Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +9 -0
- checkpoint-120/adapter_model.safetensors +3 -0
- checkpoint-120/rng_state_0.pth +3 -0
- checkpoint-120/rng_state_1.pth +3 -0
- checkpoint-120/scheduler.pt +3 -0
- checkpoint-120/training_args.bin +3 -0
- checkpoint-120/vocab.json +0 -0
- checkpoint-180/adapter_model.safetensors +3 -0
- checkpoint-180/rng_state_0.pth +3 -0
- checkpoint-180/rng_state_1.pth +3 -0
- checkpoint-180/scheduler.pt +3 -0
- checkpoint-180/tokenizer.json +3 -0
- checkpoint-180/trainer_state.json +1473 -0
- checkpoint-180/training_args.bin +3 -0
- checkpoint-180/vocab.json +0 -0
- checkpoint-240/adapter_model.safetensors +3 -0
- checkpoint-240/merges.txt +0 -0
- checkpoint-240/rng_state_0.pth +3 -0
- checkpoint-240/rng_state_1.pth +3 -0
- checkpoint-240/scheduler.pt +3 -0
- checkpoint-240/special_tokens_map.json +31 -0
- checkpoint-240/tokenizer.json +3 -0
- checkpoint-240/tokenizer_config.json +209 -0
- checkpoint-240/training_args.bin +3 -0
- checkpoint-240/vocab.json +0 -0
- checkpoint-300/adapter_model.safetensors +3 -0
- checkpoint-300/merges.txt +0 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state_1.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/tokenizer.json +3 -0
- checkpoint-300/trainer_state.json +2433 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-360/README.md +202 -0
- checkpoint-360/adapter_model.safetensors +3 -0
- checkpoint-360/rng_state_0.pth +3 -0
- checkpoint-360/scheduler.pt +3 -0
- checkpoint-360/tokenizer.json +3 -0
- checkpoint-420/README.md +202 -0
- checkpoint-420/adapter_model.safetensors +3 -0
- checkpoint-420/added_tokens.json +24 -0
- checkpoint-420/optimizer.pt +3 -0
- checkpoint-420/rng_state_0.pth +3 -0
- checkpoint-420/tokenizer.json +3 -0
- checkpoint-480/README.md +202 -0
- checkpoint-480/adapter_model.safetensors +3 -0
- checkpoint-480/merges.txt +0 -0
- checkpoint-480/optimizer.pt +3 -0
- checkpoint-480/scheduler.pt +3 -0
- checkpoint-480/special_tokens_map.json +31 -0
.gitattributes
CHANGED
|
@@ -40,3 +40,12 @@ checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 40 |
checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
checkpoint-840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
checkpoint-840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 42 |
checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
checkpoint-540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
checkpoint-480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-120/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bc41b4369c1876b6f005c2163bee18e3ee031c3d8344bba177d6cb9758ca3db
|
| 3 |
+
size 275341720
|
checkpoint-120/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c33bd105fc57bcfd4251028f79a231abc0b6d66ae04af044c1a70560a47e3d74
|
| 3 |
+
size 14512
|
checkpoint-120/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3cb7ccfc443aad8a9722133c9d10507a9f42eb4f36a5c1134581d1f5b839323
|
| 3 |
+
size 14512
|
checkpoint-120/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dd9baf01246fc9627263131baa26325e9df03b1eeb9500344dfbddaeedf522a
|
| 3 |
+
size 1064
|
checkpoint-120/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ead4a6550d360b2767d5cafb708fc1265f2158252d104b64f05a5368cafaafc9
|
| 3 |
+
size 5752
|
checkpoint-120/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-180/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80d254d1d1f790cdeff5c726d12f971b27b96422e6c0fe14b90ab3cdd4da4774
|
| 3 |
+
size 275341720
|
checkpoint-180/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:476fb9c62ce300dc06db6ad83be622afde3f1260b409f31a40493219f75cd234
|
| 3 |
+
size 14512
|
checkpoint-180/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12d10b33a82993022b517d5417c9b92a471481ea332a311cf85f5b95e39ac5e7
|
| 3 |
+
size 14512
|
checkpoint-180/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:243a9836b3d970c6c41c2092c03d3e8d49dfad7f975032e627f0fd298aca20f9
|
| 3 |
+
size 1064
|
checkpoint-180/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-180/trainer_state.json
ADDED
|
@@ -0,0 +1,1473 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9636552440290758,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 180,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016614745586708203,
|
| 13 |
+
"grad_norm": 0.050998032093048096,
|
| 14 |
+
"learning_rate": 4.999991432639962e-05,
|
| 15 |
+
"loss": 0.5487,
|
| 16 |
+
"num_input_tokens_seen": 70408,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.033229491173416406,
|
| 21 |
+
"grad_norm": 0.049370743334293365,
|
| 22 |
+
"learning_rate": 4.999965730618567e-05,
|
| 23 |
+
"loss": 0.4981,
|
| 24 |
+
"num_input_tokens_seen": 139640,
|
| 25 |
+
"step": 2
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.04984423676012461,
|
| 29 |
+
"grad_norm": 0.05077400803565979,
|
| 30 |
+
"learning_rate": 4.9999228941119745e-05,
|
| 31 |
+
"loss": 0.5505,
|
| 32 |
+
"num_input_tokens_seen": 223656,
|
| 33 |
+
"step": 3
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06645898234683281,
|
| 37 |
+
"grad_norm": 0.04397282376885414,
|
| 38 |
+
"learning_rate": 4.999862923413781e-05,
|
| 39 |
+
"loss": 0.504,
|
| 40 |
+
"num_input_tokens_seen": 300688,
|
| 41 |
+
"step": 4
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.08307372793354102,
|
| 45 |
+
"grad_norm": 0.05225864797830582,
|
| 46 |
+
"learning_rate": 4.999785818935018e-05,
|
| 47 |
+
"loss": 0.4925,
|
| 48 |
+
"num_input_tokens_seen": 366368,
|
| 49 |
+
"step": 5
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.09968847352024922,
|
| 53 |
+
"grad_norm": 0.049482282251119614,
|
| 54 |
+
"learning_rate": 4.999691581204152e-05,
|
| 55 |
+
"loss": 0.4771,
|
| 56 |
+
"num_input_tokens_seen": 445808,
|
| 57 |
+
"step": 6
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.11630321910695743,
|
| 61 |
+
"grad_norm": 0.05594080314040184,
|
| 62 |
+
"learning_rate": 4.9995802108670775e-05,
|
| 63 |
+
"loss": 0.4986,
|
| 64 |
+
"num_input_tokens_seen": 522800,
|
| 65 |
+
"step": 7
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13291796469366562,
|
| 69 |
+
"grad_norm": 0.051852282136678696,
|
| 70 |
+
"learning_rate": 4.999451708687114e-05,
|
| 71 |
+
"loss": 0.5171,
|
| 72 |
+
"num_input_tokens_seen": 599608,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.14953271028037382,
|
| 77 |
+
"grad_norm": 0.045517683029174805,
|
| 78 |
+
"learning_rate": 4.9993060755450015e-05,
|
| 79 |
+
"loss": 0.5669,
|
| 80 |
+
"num_input_tokens_seen": 681424,
|
| 81 |
+
"step": 9
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.16614745586708204,
|
| 85 |
+
"grad_norm": 0.044325754046440125,
|
| 86 |
+
"learning_rate": 4.999143312438893e-05,
|
| 87 |
+
"loss": 0.4218,
|
| 88 |
+
"num_input_tokens_seen": 756744,
|
| 89 |
+
"step": 10
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.18276220145379024,
|
| 93 |
+
"grad_norm": 0.04328459873795509,
|
| 94 |
+
"learning_rate": 4.998963420484349e-05,
|
| 95 |
+
"loss": 0.434,
|
| 96 |
+
"num_input_tokens_seen": 842576,
|
| 97 |
+
"step": 11
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.19937694704049844,
|
| 101 |
+
"grad_norm": 0.04725787043571472,
|
| 102 |
+
"learning_rate": 4.998766400914329e-05,
|
| 103 |
+
"loss": 0.4287,
|
| 104 |
+
"num_input_tokens_seen": 917232,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.21599169262720663,
|
| 109 |
+
"grad_norm": 0.03806879371404648,
|
| 110 |
+
"learning_rate": 4.9985522550791825e-05,
|
| 111 |
+
"loss": 0.3454,
|
| 112 |
+
"num_input_tokens_seen": 1006800,
|
| 113 |
+
"step": 13
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.23260643821391486,
|
| 117 |
+
"grad_norm": 0.05201176926493645,
|
| 118 |
+
"learning_rate": 4.998320984446641e-05,
|
| 119 |
+
"loss": 0.436,
|
| 120 |
+
"num_input_tokens_seen": 1085824,
|
| 121 |
+
"step": 14
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.24922118380062305,
|
| 125 |
+
"grad_norm": 0.047955628484487534,
|
| 126 |
+
"learning_rate": 4.9980725906018074e-05,
|
| 127 |
+
"loss": 0.4625,
|
| 128 |
+
"num_input_tokens_seen": 1164160,
|
| 129 |
+
"step": 15
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.26583592938733125,
|
| 133 |
+
"grad_norm": 0.05529098957777023,
|
| 134 |
+
"learning_rate": 4.997807075247146e-05,
|
| 135 |
+
"loss": 0.5035,
|
| 136 |
+
"num_input_tokens_seen": 1242264,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.2824506749740395,
|
| 141 |
+
"grad_norm": 0.04751162976026535,
|
| 142 |
+
"learning_rate": 4.997524440202469e-05,
|
| 143 |
+
"loss": 0.4354,
|
| 144 |
+
"num_input_tokens_seen": 1325904,
|
| 145 |
+
"step": 17
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.29906542056074764,
|
| 149 |
+
"grad_norm": 0.06726882606744766,
|
| 150 |
+
"learning_rate": 4.9972246874049254e-05,
|
| 151 |
+
"loss": 0.5439,
|
| 152 |
+
"num_input_tokens_seen": 1385632,
|
| 153 |
+
"step": 18
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.31568016614745587,
|
| 157 |
+
"grad_norm": 0.05245920270681381,
|
| 158 |
+
"learning_rate": 4.996907818908987e-05,
|
| 159 |
+
"loss": 0.3727,
|
| 160 |
+
"num_input_tokens_seen": 1470632,
|
| 161 |
+
"step": 19
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.3322949117341641,
|
| 165 |
+
"grad_norm": 0.05745376646518707,
|
| 166 |
+
"learning_rate": 4.996573836886435e-05,
|
| 167 |
+
"loss": 0.4894,
|
| 168 |
+
"num_input_tokens_seen": 1547536,
|
| 169 |
+
"step": 20
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.34890965732087226,
|
| 173 |
+
"grad_norm": 0.056607529520988464,
|
| 174 |
+
"learning_rate": 4.9962227436263453e-05,
|
| 175 |
+
"loss": 0.3846,
|
| 176 |
+
"num_input_tokens_seen": 1615528,
|
| 177 |
+
"step": 21
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3655244029075805,
|
| 181 |
+
"grad_norm": 0.06150667741894722,
|
| 182 |
+
"learning_rate": 4.995854541535071e-05,
|
| 183 |
+
"loss": 0.4362,
|
| 184 |
+
"num_input_tokens_seen": 1694352,
|
| 185 |
+
"step": 22
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3821391484942887,
|
| 189 |
+
"grad_norm": 0.056484442204236984,
|
| 190 |
+
"learning_rate": 4.9954692331362294e-05,
|
| 191 |
+
"loss": 0.4438,
|
| 192 |
+
"num_input_tokens_seen": 1753776,
|
| 193 |
+
"step": 23
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.3987538940809969,
|
| 197 |
+
"grad_norm": 0.0704159140586853,
|
| 198 |
+
"learning_rate": 4.995066821070679e-05,
|
| 199 |
+
"loss": 0.4496,
|
| 200 |
+
"num_input_tokens_seen": 1809048,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.4153686396677051,
|
| 205 |
+
"grad_norm": 0.06202029809355736,
|
| 206 |
+
"learning_rate": 4.994647308096509e-05,
|
| 207 |
+
"loss": 0.5096,
|
| 208 |
+
"num_input_tokens_seen": 1884264,
|
| 209 |
+
"step": 25
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.43198338525441327,
|
| 213 |
+
"grad_norm": 0.04237145930528641,
|
| 214 |
+
"learning_rate": 4.994210697089014e-05,
|
| 215 |
+
"loss": 0.3722,
|
| 216 |
+
"num_input_tokens_seen": 1981704,
|
| 217 |
+
"step": 26
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.4485981308411215,
|
| 221 |
+
"grad_norm": 0.06920398026704788,
|
| 222 |
+
"learning_rate": 4.9937569910406756e-05,
|
| 223 |
+
"loss": 0.4103,
|
| 224 |
+
"num_input_tokens_seen": 2044144,
|
| 225 |
+
"step": 27
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.4652128764278297,
|
| 229 |
+
"grad_norm": 0.062432270497083664,
|
| 230 |
+
"learning_rate": 4.9932861930611454e-05,
|
| 231 |
+
"loss": 0.357,
|
| 232 |
+
"num_input_tokens_seen": 2107584,
|
| 233 |
+
"step": 28
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4818276220145379,
|
| 237 |
+
"grad_norm": 0.06791180372238159,
|
| 238 |
+
"learning_rate": 4.9927983063772196e-05,
|
| 239 |
+
"loss": 0.3889,
|
| 240 |
+
"num_input_tokens_seen": 2169248,
|
| 241 |
+
"step": 29
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4984423676012461,
|
| 245 |
+
"grad_norm": 0.07219590991735458,
|
| 246 |
+
"learning_rate": 4.99229333433282e-05,
|
| 247 |
+
"loss": 0.3543,
|
| 248 |
+
"num_input_tokens_seen": 2230344,
|
| 249 |
+
"step": 30
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.5150571131879543,
|
| 253 |
+
"grad_norm": 0.0647474005818367,
|
| 254 |
+
"learning_rate": 4.9917712803889674e-05,
|
| 255 |
+
"loss": 0.3453,
|
| 256 |
+
"num_input_tokens_seen": 2302368,
|
| 257 |
+
"step": 31
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.5316718587746625,
|
| 261 |
+
"grad_norm": 0.07434642314910889,
|
| 262 |
+
"learning_rate": 4.991232148123761e-05,
|
| 263 |
+
"loss": 0.435,
|
| 264 |
+
"num_input_tokens_seen": 2369984,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.5482866043613707,
|
| 269 |
+
"grad_norm": 0.05302443355321884,
|
| 270 |
+
"learning_rate": 4.990675941232353e-05,
|
| 271 |
+
"loss": 0.3981,
|
| 272 |
+
"num_input_tokens_seen": 2453032,
|
| 273 |
+
"step": 33
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.564901349948079,
|
| 277 |
+
"grad_norm": 0.053745292127132416,
|
| 278 |
+
"learning_rate": 4.990102663526924e-05,
|
| 279 |
+
"loss": 0.3755,
|
| 280 |
+
"num_input_tokens_seen": 2527464,
|
| 281 |
+
"step": 34
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.5815160955347871,
|
| 285 |
+
"grad_norm": 0.06717613339424133,
|
| 286 |
+
"learning_rate": 4.989512318936655e-05,
|
| 287 |
+
"loss": 0.3699,
|
| 288 |
+
"num_input_tokens_seen": 2597032,
|
| 289 |
+
"step": 35
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5981308411214953,
|
| 293 |
+
"grad_norm": 0.071847103536129,
|
| 294 |
+
"learning_rate": 4.9889049115077005e-05,
|
| 295 |
+
"loss": 0.3705,
|
| 296 |
+
"num_input_tokens_seen": 2671704,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.6147455867082036,
|
| 301 |
+
"grad_norm": 0.0460306741297245,
|
| 302 |
+
"learning_rate": 4.988280445403164e-05,
|
| 303 |
+
"loss": 0.3797,
|
| 304 |
+
"num_input_tokens_seen": 2767640,
|
| 305 |
+
"step": 37
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.6313603322949117,
|
| 309 |
+
"grad_norm": 0.053273387253284454,
|
| 310 |
+
"learning_rate": 4.987638924903067e-05,
|
| 311 |
+
"loss": 0.3799,
|
| 312 |
+
"num_input_tokens_seen": 2843720,
|
| 313 |
+
"step": 38
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.6479750778816199,
|
| 317 |
+
"grad_norm": 0.05600422993302345,
|
| 318 |
+
"learning_rate": 4.9869803544043166e-05,
|
| 319 |
+
"loss": 0.2866,
|
| 320 |
+
"num_input_tokens_seen": 2921472,
|
| 321 |
+
"step": 39
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.6645898234683282,
|
| 325 |
+
"grad_norm": 0.06414052098989487,
|
| 326 |
+
"learning_rate": 4.9863047384206835e-05,
|
| 327 |
+
"loss": 0.4115,
|
| 328 |
+
"num_input_tokens_seen": 2998400,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.6812045690550363,
|
| 333 |
+
"grad_norm": 0.09214208275079727,
|
| 334 |
+
"learning_rate": 4.985612081582764e-05,
|
| 335 |
+
"loss": 0.3804,
|
| 336 |
+
"num_input_tokens_seen": 3059648,
|
| 337 |
+
"step": 41
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.6978193146417445,
|
| 341 |
+
"grad_norm": 0.0555964931845665,
|
| 342 |
+
"learning_rate": 4.98490238863795e-05,
|
| 343 |
+
"loss": 0.3121,
|
| 344 |
+
"num_input_tokens_seen": 3140184,
|
| 345 |
+
"step": 42
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7144340602284528,
|
| 349 |
+
"grad_norm": 0.06256969273090363,
|
| 350 |
+
"learning_rate": 4.984175664450397e-05,
|
| 351 |
+
"loss": 0.3271,
|
| 352 |
+
"num_input_tokens_seen": 3207184,
|
| 353 |
+
"step": 43
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.731048805815161,
|
| 357 |
+
"grad_norm": 0.0543232187628746,
|
| 358 |
+
"learning_rate": 4.983431914000991e-05,
|
| 359 |
+
"loss": 0.364,
|
| 360 |
+
"num_input_tokens_seen": 3292344,
|
| 361 |
+
"step": 44
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.7476635514018691,
|
| 365 |
+
"grad_norm": 0.06077824532985687,
|
| 366 |
+
"learning_rate": 4.982671142387316e-05,
|
| 367 |
+
"loss": 0.3894,
|
| 368 |
+
"num_input_tokens_seen": 3365384,
|
| 369 |
+
"step": 45
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.7642782969885774,
|
| 373 |
+
"grad_norm": 0.06091070920228958,
|
| 374 |
+
"learning_rate": 4.981893354823614e-05,
|
| 375 |
+
"loss": 0.3354,
|
| 376 |
+
"num_input_tokens_seen": 3440720,
|
| 377 |
+
"step": 46
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.7808930425752856,
|
| 381 |
+
"grad_norm": 0.054153311997652054,
|
| 382 |
+
"learning_rate": 4.9810985566407544e-05,
|
| 383 |
+
"loss": 0.3058,
|
| 384 |
+
"num_input_tokens_seen": 3533576,
|
| 385 |
+
"step": 47
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.7975077881619937,
|
| 389 |
+
"grad_norm": 0.06662417948246002,
|
| 390 |
+
"learning_rate": 4.980286753286195e-05,
|
| 391 |
+
"loss": 0.4658,
|
| 392 |
+
"num_input_tokens_seen": 3599744,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.814122533748702,
|
| 397 |
+
"grad_norm": 0.05790851265192032,
|
| 398 |
+
"learning_rate": 4.979457950323945e-05,
|
| 399 |
+
"loss": 0.3647,
|
| 400 |
+
"num_input_tokens_seen": 3689520,
|
| 401 |
+
"step": 49
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8307372793354102,
|
| 405 |
+
"grad_norm": 0.10742159187793732,
|
| 406 |
+
"learning_rate": 4.9786121534345265e-05,
|
| 407 |
+
"loss": 0.343,
|
| 408 |
+
"num_input_tokens_seen": 3751808,
|
| 409 |
+
"step": 50
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.8473520249221184,
|
| 413 |
+
"grad_norm": 0.05565556138753891,
|
| 414 |
+
"learning_rate": 4.9777493684149375e-05,
|
| 415 |
+
"loss": 0.3317,
|
| 416 |
+
"num_input_tokens_seen": 3839096,
|
| 417 |
+
"step": 51
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.8639667705088265,
|
| 421 |
+
"grad_norm": 0.05752381682395935,
|
| 422 |
+
"learning_rate": 4.976869601178609e-05,
|
| 423 |
+
"loss": 0.38,
|
| 424 |
+
"num_input_tokens_seen": 3919824,
|
| 425 |
+
"step": 52
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.8805815160955348,
|
| 429 |
+
"grad_norm": 0.06406434625387192,
|
| 430 |
+
"learning_rate": 4.975972857755369e-05,
|
| 431 |
+
"loss": 0.2676,
|
| 432 |
+
"num_input_tokens_seen": 3989312,
|
| 433 |
+
"step": 53
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.897196261682243,
|
| 437 |
+
"grad_norm": 0.0653691440820694,
|
| 438 |
+
"learning_rate": 4.975059144291394e-05,
|
| 439 |
+
"loss": 0.3516,
|
| 440 |
+
"num_input_tokens_seen": 4060528,
|
| 441 |
+
"step": 54
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.9138110072689511,
|
| 445 |
+
"grad_norm": 0.06272953748703003,
|
| 446 |
+
"learning_rate": 4.974128467049176e-05,
|
| 447 |
+
"loss": 0.3004,
|
| 448 |
+
"num_input_tokens_seen": 4129368,
|
| 449 |
+
"step": 55
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.9304257528556594,
|
| 453 |
+
"grad_norm": 0.08054930716753006,
|
| 454 |
+
"learning_rate": 4.9731808324074717e-05,
|
| 455 |
+
"loss": 0.3009,
|
| 456 |
+
"num_input_tokens_seen": 4175208,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9470404984423676,
|
| 461 |
+
"grad_norm": 0.07523038238286972,
|
| 462 |
+
"learning_rate": 4.972216246861262e-05,
|
| 463 |
+
"loss": 0.2814,
|
| 464 |
+
"num_input_tokens_seen": 4218096,
|
| 465 |
+
"step": 57
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.9636552440290758,
|
| 469 |
+
"grad_norm": 0.07347433269023895,
|
| 470 |
+
"learning_rate": 4.971234717021709e-05,
|
| 471 |
+
"loss": 0.3321,
|
| 472 |
+
"num_input_tokens_seen": 4275968,
|
| 473 |
+
"step": 58
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.980269989615784,
|
| 477 |
+
"grad_norm": 0.05830248445272446,
|
| 478 |
+
"learning_rate": 4.9702362496161085e-05,
|
| 479 |
+
"loss": 0.2881,
|
| 480 |
+
"num_input_tokens_seen": 4346616,
|
| 481 |
+
"step": 59
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.9968847352024922,
|
| 485 |
+
"grad_norm": 0.061629410833120346,
|
| 486 |
+
"learning_rate": 4.9692208514878444e-05,
|
| 487 |
+
"loss": 0.2993,
|
| 488 |
+
"num_input_tokens_seen": 4425064,
|
| 489 |
+
"step": 60
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.0,
|
| 493 |
+
"grad_norm": 0.13380740582942963,
|
| 494 |
+
"learning_rate": 4.968188529596342e-05,
|
| 495 |
+
"loss": 0.2511,
|
| 496 |
+
"num_input_tokens_seen": 4435328,
|
| 497 |
+
"step": 61
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.0166147455867083,
|
| 501 |
+
"grad_norm": 0.0726238414645195,
|
| 502 |
+
"learning_rate": 4.9671392910170185e-05,
|
| 503 |
+
"loss": 0.3127,
|
| 504 |
+
"num_input_tokens_seen": 4500104,
|
| 505 |
+
"step": 62
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.0332294911734163,
|
| 509 |
+
"grad_norm": 0.05980083718895912,
|
| 510 |
+
"learning_rate": 4.966073142941239e-05,
|
| 511 |
+
"loss": 0.3601,
|
| 512 |
+
"num_input_tokens_seen": 4581976,
|
| 513 |
+
"step": 63
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.0498442367601246,
|
| 517 |
+
"grad_norm": 0.06445376574993134,
|
| 518 |
+
"learning_rate": 4.964990092676263e-05,
|
| 519 |
+
"loss": 0.3049,
|
| 520 |
+
"num_input_tokens_seen": 4652160,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.066458982346833,
|
| 525 |
+
"grad_norm": 0.07824505120515823,
|
| 526 |
+
"learning_rate": 4.9638901476451946e-05,
|
| 527 |
+
"loss": 0.3099,
|
| 528 |
+
"num_input_tokens_seen": 4709368,
|
| 529 |
+
"step": 65
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.083073727933541,
|
| 533 |
+
"grad_norm": 0.058268457651138306,
|
| 534 |
+
"learning_rate": 4.962773315386935e-05,
|
| 535 |
+
"loss": 0.3273,
|
| 536 |
+
"num_input_tokens_seen": 4798256,
|
| 537 |
+
"step": 66
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.0996884735202492,
|
| 541 |
+
"grad_norm": 0.07069691270589828,
|
| 542 |
+
"learning_rate": 4.961639603556127e-05,
|
| 543 |
+
"loss": 0.282,
|
| 544 |
+
"num_input_tokens_seen": 4859200,
|
| 545 |
+
"step": 67
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.1163032191069575,
|
| 549 |
+
"grad_norm": 0.0775996670126915,
|
| 550 |
+
"learning_rate": 4.960489019923105e-05,
|
| 551 |
+
"loss": 0.3642,
|
| 552 |
+
"num_input_tokens_seen": 4925992,
|
| 553 |
+
"step": 68
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.1329179646936656,
|
| 557 |
+
"grad_norm": 0.07044171541929245,
|
| 558 |
+
"learning_rate": 4.9593215723738404e-05,
|
| 559 |
+
"loss": 0.2896,
|
| 560 |
+
"num_input_tokens_seen": 4998808,
|
| 561 |
+
"step": 69
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.1495327102803738,
|
| 565 |
+
"grad_norm": 0.05971802771091461,
|
| 566 |
+
"learning_rate": 4.958137268909887e-05,
|
| 567 |
+
"loss": 0.2578,
|
| 568 |
+
"num_input_tokens_seen": 5089672,
|
| 569 |
+
"step": 70
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.1661474558670821,
|
| 573 |
+
"grad_norm": 0.07145556062459946,
|
| 574 |
+
"learning_rate": 4.9569361176483286e-05,
|
| 575 |
+
"loss": 0.3243,
|
| 576 |
+
"num_input_tokens_seen": 5166744,
|
| 577 |
+
"step": 71
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.1827622014537902,
|
| 581 |
+
"grad_norm": 0.07455787807703018,
|
| 582 |
+
"learning_rate": 4.9557181268217227e-05,
|
| 583 |
+
"loss": 0.3949,
|
| 584 |
+
"num_input_tokens_seen": 5228264,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.1993769470404985,
|
| 589 |
+
"grad_norm": 0.055582575500011444,
|
| 590 |
+
"learning_rate": 4.9544833047780394e-05,
|
| 591 |
+
"loss": 0.2877,
|
| 592 |
+
"num_input_tokens_seen": 5338224,
|
| 593 |
+
"step": 73
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.2159916926272065,
|
| 597 |
+
"grad_norm": 0.07675391435623169,
|
| 598 |
+
"learning_rate": 4.9532316599806124e-05,
|
| 599 |
+
"loss": 0.3152,
|
| 600 |
+
"num_input_tokens_seen": 5399848,
|
| 601 |
+
"step": 74
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.2326064382139148,
|
| 605 |
+
"grad_norm": 0.08048644661903381,
|
| 606 |
+
"learning_rate": 4.951963201008076e-05,
|
| 607 |
+
"loss": 0.2976,
|
| 608 |
+
"num_input_tokens_seen": 5468624,
|
| 609 |
+
"step": 75
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.249221183800623,
|
| 613 |
+
"grad_norm": 0.07579060643911362,
|
| 614 |
+
"learning_rate": 4.9506779365543046e-05,
|
| 615 |
+
"loss": 0.2982,
|
| 616 |
+
"num_input_tokens_seen": 5536776,
|
| 617 |
+
"step": 76
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.2658359293873311,
|
| 621 |
+
"grad_norm": 0.07828006893396378,
|
| 622 |
+
"learning_rate": 4.949375875428357e-05,
|
| 623 |
+
"loss": 0.3272,
|
| 624 |
+
"num_input_tokens_seen": 5609296,
|
| 625 |
+
"step": 77
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.2824506749740394,
|
| 629 |
+
"grad_norm": 0.08079098165035248,
|
| 630 |
+
"learning_rate": 4.9480570265544144e-05,
|
| 631 |
+
"loss": 0.2768,
|
| 632 |
+
"num_input_tokens_seen": 5663824,
|
| 633 |
+
"step": 78
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.2990654205607477,
|
| 637 |
+
"grad_norm": 0.07579358667135239,
|
| 638 |
+
"learning_rate": 4.94672139897172e-05,
|
| 639 |
+
"loss": 0.318,
|
| 640 |
+
"num_input_tokens_seen": 5742032,
|
| 641 |
+
"step": 79
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.3156801661474558,
|
| 645 |
+
"grad_norm": 0.07588379085063934,
|
| 646 |
+
"learning_rate": 4.9453690018345144e-05,
|
| 647 |
+
"loss": 0.3007,
|
| 648 |
+
"num_input_tokens_seen": 5816864,
|
| 649 |
+
"step": 80
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.332294911734164,
|
| 653 |
+
"grad_norm": 0.08709035068750381,
|
| 654 |
+
"learning_rate": 4.943999844411977e-05,
|
| 655 |
+
"loss": 0.2797,
|
| 656 |
+
"num_input_tokens_seen": 5881624,
|
| 657 |
+
"step": 81
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.3489096573208723,
|
| 661 |
+
"grad_norm": 0.05975884944200516,
|
| 662 |
+
"learning_rate": 4.94261393608816e-05,
|
| 663 |
+
"loss": 0.2591,
|
| 664 |
+
"num_input_tokens_seen": 5970272,
|
| 665 |
+
"step": 82
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.3655244029075804,
|
| 669 |
+
"grad_norm": 0.07372818142175674,
|
| 670 |
+
"learning_rate": 4.941211286361922e-05,
|
| 671 |
+
"loss": 0.2687,
|
| 672 |
+
"num_input_tokens_seen": 6058752,
|
| 673 |
+
"step": 83
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.3821391484942886,
|
| 677 |
+
"grad_norm": 0.09071576595306396,
|
| 678 |
+
"learning_rate": 4.939791904846869e-05,
|
| 679 |
+
"loss": 0.2979,
|
| 680 |
+
"num_input_tokens_seen": 6120064,
|
| 681 |
+
"step": 84
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.398753894080997,
|
| 685 |
+
"grad_norm": 0.0849960595369339,
|
| 686 |
+
"learning_rate": 4.938355801271282e-05,
|
| 687 |
+
"loss": 0.2927,
|
| 688 |
+
"num_input_tokens_seen": 6182072,
|
| 689 |
+
"step": 85
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.415368639667705,
|
| 693 |
+
"grad_norm": 0.08258760720491409,
|
| 694 |
+
"learning_rate": 4.936902985478055e-05,
|
| 695 |
+
"loss": 0.295,
|
| 696 |
+
"num_input_tokens_seen": 6269680,
|
| 697 |
+
"step": 86
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.4319833852544133,
|
| 701 |
+
"grad_norm": 0.0851503536105156,
|
| 702 |
+
"learning_rate": 4.935433467424624e-05,
|
| 703 |
+
"loss": 0.2925,
|
| 704 |
+
"num_input_tokens_seen": 6347424,
|
| 705 |
+
"step": 87
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.4485981308411215,
|
| 709 |
+
"grad_norm": 0.08852345496416092,
|
| 710 |
+
"learning_rate": 4.933947257182901e-05,
|
| 711 |
+
"loss": 0.3153,
|
| 712 |
+
"num_input_tokens_seen": 6412584,
|
| 713 |
+
"step": 88
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.4652128764278296,
|
| 717 |
+
"grad_norm": 0.08184897154569626,
|
| 718 |
+
"learning_rate": 4.932444364939205e-05,
|
| 719 |
+
"loss": 0.292,
|
| 720 |
+
"num_input_tokens_seen": 6482728,
|
| 721 |
+
"step": 89
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.4818276220145379,
|
| 725 |
+
"grad_norm": 0.08270515501499176,
|
| 726 |
+
"learning_rate": 4.9309248009941914e-05,
|
| 727 |
+
"loss": 0.3472,
|
| 728 |
+
"num_input_tokens_seen": 6562104,
|
| 729 |
+
"step": 90
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.4984423676012462,
|
| 733 |
+
"grad_norm": 0.07407747954130173,
|
| 734 |
+
"learning_rate": 4.929388575762782e-05,
|
| 735 |
+
"loss": 0.2995,
|
| 736 |
+
"num_input_tokens_seen": 6656552,
|
| 737 |
+
"step": 91
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.5150571131879542,
|
| 741 |
+
"grad_norm": 0.08710360527038574,
|
| 742 |
+
"learning_rate": 4.9278356997740904e-05,
|
| 743 |
+
"loss": 0.2549,
|
| 744 |
+
"num_input_tokens_seen": 6714184,
|
| 745 |
+
"step": 92
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.5316718587746625,
|
| 749 |
+
"grad_norm": 0.0773790255188942,
|
| 750 |
+
"learning_rate": 4.9262661836713564e-05,
|
| 751 |
+
"loss": 0.2814,
|
| 752 |
+
"num_input_tokens_seen": 6793552,
|
| 753 |
+
"step": 93
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.5482866043613708,
|
| 757 |
+
"grad_norm": 0.1002134457230568,
|
| 758 |
+
"learning_rate": 4.924680038211867e-05,
|
| 759 |
+
"loss": 0.2876,
|
| 760 |
+
"num_input_tokens_seen": 6865256,
|
| 761 |
+
"step": 94
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.5649013499480788,
|
| 765 |
+
"grad_norm": 0.09670394659042358,
|
| 766 |
+
"learning_rate": 4.9230772742668866e-05,
|
| 767 |
+
"loss": 0.2846,
|
| 768 |
+
"num_input_tokens_seen": 6931152,
|
| 769 |
+
"step": 95
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.5815160955347871,
|
| 773 |
+
"grad_norm": 0.08910100907087326,
|
| 774 |
+
"learning_rate": 4.9214579028215776e-05,
|
| 775 |
+
"loss": 0.2944,
|
| 776 |
+
"num_input_tokens_seen": 6998408,
|
| 777 |
+
"step": 96
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.5981308411214954,
|
| 781 |
+
"grad_norm": 0.09202459454536438,
|
| 782 |
+
"learning_rate": 4.919821934974933e-05,
|
| 783 |
+
"loss": 0.251,
|
| 784 |
+
"num_input_tokens_seen": 7053008,
|
| 785 |
+
"step": 97
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.6147455867082035,
|
| 789 |
+
"grad_norm": 0.10218881815671921,
|
| 790 |
+
"learning_rate": 4.918169381939692e-05,
|
| 791 |
+
"loss": 0.2851,
|
| 792 |
+
"num_input_tokens_seen": 7106440,
|
| 793 |
+
"step": 98
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.6313603322949117,
|
| 797 |
+
"grad_norm": 0.09290914982557297,
|
| 798 |
+
"learning_rate": 4.916500255042268e-05,
|
| 799 |
+
"loss": 0.2959,
|
| 800 |
+
"num_input_tokens_seen": 7167032,
|
| 801 |
+
"step": 99
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.64797507788162,
|
| 805 |
+
"grad_norm": 0.07791033387184143,
|
| 806 |
+
"learning_rate": 4.914814565722671e-05,
|
| 807 |
+
"loss": 0.2481,
|
| 808 |
+
"num_input_tokens_seen": 7245720,
|
| 809 |
+
"step": 100
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.664589823468328,
|
| 813 |
+
"grad_norm": 0.08885534107685089,
|
| 814 |
+
"learning_rate": 4.913112325534426e-05,
|
| 815 |
+
"loss": 0.3168,
|
| 816 |
+
"num_input_tokens_seen": 7326320,
|
| 817 |
+
"step": 101
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.6812045690550363,
|
| 821 |
+
"grad_norm": 0.08569750934839249,
|
| 822 |
+
"learning_rate": 4.9113935461444955e-05,
|
| 823 |
+
"loss": 0.2805,
|
| 824 |
+
"num_input_tokens_seen": 7442232,
|
| 825 |
+
"step": 102
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.6978193146417446,
|
| 829 |
+
"grad_norm": 0.1112508773803711,
|
| 830 |
+
"learning_rate": 4.9096582393332025e-05,
|
| 831 |
+
"loss": 0.2675,
|
| 832 |
+
"num_input_tokens_seen": 7502496,
|
| 833 |
+
"step": 103
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.7144340602284527,
|
| 837 |
+
"grad_norm": 0.09654372185468674,
|
| 838 |
+
"learning_rate": 4.907906416994146e-05,
|
| 839 |
+
"loss": 0.3038,
|
| 840 |
+
"num_input_tokens_seen": 7566496,
|
| 841 |
+
"step": 104
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.731048805815161,
|
| 845 |
+
"grad_norm": 0.10022995620965958,
|
| 846 |
+
"learning_rate": 4.906138091134118e-05,
|
| 847 |
+
"loss": 0.3639,
|
| 848 |
+
"num_input_tokens_seen": 7629056,
|
| 849 |
+
"step": 105
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.7476635514018692,
|
| 853 |
+
"grad_norm": 0.08336564153432846,
|
| 854 |
+
"learning_rate": 4.9043532738730284e-05,
|
| 855 |
+
"loss": 0.2944,
|
| 856 |
+
"num_input_tokens_seen": 7706096,
|
| 857 |
+
"step": 106
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.7642782969885773,
|
| 861 |
+
"grad_norm": 0.08539658784866333,
|
| 862 |
+
"learning_rate": 4.9025519774438136e-05,
|
| 863 |
+
"loss": 0.2392,
|
| 864 |
+
"num_input_tokens_seen": 7780072,
|
| 865 |
+
"step": 107
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.7808930425752856,
|
| 869 |
+
"grad_norm": 0.09139693528413773,
|
| 870 |
+
"learning_rate": 4.900734214192358e-05,
|
| 871 |
+
"loss": 0.2685,
|
| 872 |
+
"num_input_tokens_seen": 7857712,
|
| 873 |
+
"step": 108
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.7975077881619939,
|
| 877 |
+
"grad_norm": 0.1043916717171669,
|
| 878 |
+
"learning_rate": 4.898899996577407e-05,
|
| 879 |
+
"loss": 0.2513,
|
| 880 |
+
"num_input_tokens_seen": 7916832,
|
| 881 |
+
"step": 109
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.814122533748702,
|
| 885 |
+
"grad_norm": 0.09203662723302841,
|
| 886 |
+
"learning_rate": 4.8970493371704826e-05,
|
| 887 |
+
"loss": 0.2974,
|
| 888 |
+
"num_input_tokens_seen": 7993056,
|
| 889 |
+
"step": 110
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.8307372793354102,
|
| 893 |
+
"grad_norm": 0.09319474548101425,
|
| 894 |
+
"learning_rate": 4.8951822486557986e-05,
|
| 895 |
+
"loss": 0.3096,
|
| 896 |
+
"num_input_tokens_seen": 8090056,
|
| 897 |
+
"step": 111
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.8473520249221185,
|
| 901 |
+
"grad_norm": 0.10193445533514023,
|
| 902 |
+
"learning_rate": 4.893298743830168e-05,
|
| 903 |
+
"loss": 0.2633,
|
| 904 |
+
"num_input_tokens_seen": 8164808,
|
| 905 |
+
"step": 112
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.8639667705088265,
|
| 909 |
+
"grad_norm": 0.11407948285341263,
|
| 910 |
+
"learning_rate": 4.891398835602925e-05,
|
| 911 |
+
"loss": 0.2584,
|
| 912 |
+
"num_input_tokens_seen": 8223568,
|
| 913 |
+
"step": 113
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.8805815160955348,
|
| 917 |
+
"grad_norm": 0.11977085471153259,
|
| 918 |
+
"learning_rate": 4.8894825369958255e-05,
|
| 919 |
+
"loss": 0.2619,
|
| 920 |
+
"num_input_tokens_seen": 8276160,
|
| 921 |
+
"step": 114
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.897196261682243,
|
| 925 |
+
"grad_norm": 0.10925433784723282,
|
| 926 |
+
"learning_rate": 4.8875498611429674e-05,
|
| 927 |
+
"loss": 0.2762,
|
| 928 |
+
"num_input_tokens_seen": 8354904,
|
| 929 |
+
"step": 115
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.9138110072689511,
|
| 933 |
+
"grad_norm": 0.09673939645290375,
|
| 934 |
+
"learning_rate": 4.8856008212906925e-05,
|
| 935 |
+
"loss": 0.3152,
|
| 936 |
+
"num_input_tokens_seen": 8442584,
|
| 937 |
+
"step": 116
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.9304257528556594,
|
| 941 |
+
"grad_norm": 0.10827789455652237,
|
| 942 |
+
"learning_rate": 4.8836354307975026e-05,
|
| 943 |
+
"loss": 0.2759,
|
| 944 |
+
"num_input_tokens_seen": 8506688,
|
| 945 |
+
"step": 117
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.9470404984423677,
|
| 949 |
+
"grad_norm": 0.08390220254659653,
|
| 950 |
+
"learning_rate": 4.881653703133966e-05,
|
| 951 |
+
"loss": 0.2192,
|
| 952 |
+
"num_input_tokens_seen": 8610712,
|
| 953 |
+
"step": 118
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.9636552440290758,
|
| 957 |
+
"grad_norm": 0.09252211451530457,
|
| 958 |
+
"learning_rate": 4.87965565188262e-05,
|
| 959 |
+
"loss": 0.2618,
|
| 960 |
+
"num_input_tokens_seen": 8692624,
|
| 961 |
+
"step": 119
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.980269989615784,
|
| 965 |
+
"grad_norm": 0.1107102632522583,
|
| 966 |
+
"learning_rate": 4.877641290737884e-05,
|
| 967 |
+
"loss": 0.2666,
|
| 968 |
+
"num_input_tokens_seen": 8772208,
|
| 969 |
+
"step": 120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.9968847352024923,
|
| 973 |
+
"grad_norm": 0.0917077362537384,
|
| 974 |
+
"learning_rate": 4.8756106335059646e-05,
|
| 975 |
+
"loss": 0.253,
|
| 976 |
+
"num_input_tokens_seen": 8854904,
|
| 977 |
+
"step": 121
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.0,
|
| 981 |
+
"grad_norm": 0.2606711685657501,
|
| 982 |
+
"learning_rate": 4.87356369410476e-05,
|
| 983 |
+
"loss": 0.235,
|
| 984 |
+
"num_input_tokens_seen": 8872656,
|
| 985 |
+
"step": 122
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.016614745586708,
|
| 989 |
+
"grad_norm": 0.10363993793725967,
|
| 990 |
+
"learning_rate": 4.8715004865637614e-05,
|
| 991 |
+
"loss": 0.266,
|
| 992 |
+
"num_input_tokens_seen": 8946480,
|
| 993 |
+
"step": 123
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.0332294911734166,
|
| 997 |
+
"grad_norm": 0.09997844696044922,
|
| 998 |
+
"learning_rate": 4.869421025023965e-05,
|
| 999 |
+
"loss": 0.2696,
|
| 1000 |
+
"num_input_tokens_seen": 9023328,
|
| 1001 |
+
"step": 124
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 2.0498442367601246,
|
| 1005 |
+
"grad_norm": 0.13349319994449615,
|
| 1006 |
+
"learning_rate": 4.867325323737765e-05,
|
| 1007 |
+
"loss": 0.2552,
|
| 1008 |
+
"num_input_tokens_seen": 9074320,
|
| 1009 |
+
"step": 125
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 2.0664589823468327,
|
| 1013 |
+
"grad_norm": 0.11201464384794235,
|
| 1014 |
+
"learning_rate": 4.8652133970688636e-05,
|
| 1015 |
+
"loss": 0.2486,
|
| 1016 |
+
"num_input_tokens_seen": 9148784,
|
| 1017 |
+
"step": 126
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.083073727933541,
|
| 1021 |
+
"grad_norm": 0.10193142294883728,
|
| 1022 |
+
"learning_rate": 4.8630852594921706e-05,
|
| 1023 |
+
"loss": 0.2814,
|
| 1024 |
+
"num_input_tokens_seen": 9246624,
|
| 1025 |
+
"step": 127
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.0996884735202492,
|
| 1029 |
+
"grad_norm": 0.1305130422115326,
|
| 1030 |
+
"learning_rate": 4.860940925593703e-05,
|
| 1031 |
+
"loss": 0.304,
|
| 1032 |
+
"num_input_tokens_seen": 9328176,
|
| 1033 |
+
"step": 128
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.1163032191069573,
|
| 1037 |
+
"grad_norm": 0.1137692779302597,
|
| 1038 |
+
"learning_rate": 4.8587804100704845e-05,
|
| 1039 |
+
"loss": 0.2427,
|
| 1040 |
+
"num_input_tokens_seen": 9388936,
|
| 1041 |
+
"step": 129
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.132917964693666,
|
| 1045 |
+
"grad_norm": 0.12126237154006958,
|
| 1046 |
+
"learning_rate": 4.856603727730447e-05,
|
| 1047 |
+
"loss": 0.2485,
|
| 1048 |
+
"num_input_tokens_seen": 9461664,
|
| 1049 |
+
"step": 130
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.149532710280374,
|
| 1053 |
+
"grad_norm": 0.11567176878452301,
|
| 1054 |
+
"learning_rate": 4.854410893492326e-05,
|
| 1055 |
+
"loss": 0.2628,
|
| 1056 |
+
"num_input_tokens_seen": 9535000,
|
| 1057 |
+
"step": 131
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 2.166147455867082,
|
| 1061 |
+
"grad_norm": 0.1399552971124649,
|
| 1062 |
+
"learning_rate": 4.852201922385564e-05,
|
| 1063 |
+
"loss": 0.2518,
|
| 1064 |
+
"num_input_tokens_seen": 9600296,
|
| 1065 |
+
"step": 132
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.1827622014537904,
|
| 1069 |
+
"grad_norm": 0.13912151753902435,
|
| 1070 |
+
"learning_rate": 4.8499768295502004e-05,
|
| 1071 |
+
"loss": 0.2429,
|
| 1072 |
+
"num_input_tokens_seen": 9686784,
|
| 1073 |
+
"step": 133
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.1993769470404985,
|
| 1077 |
+
"grad_norm": 0.11130474507808685,
|
| 1078 |
+
"learning_rate": 4.847735630236773e-05,
|
| 1079 |
+
"loss": 0.2775,
|
| 1080 |
+
"num_input_tokens_seen": 9781112,
|
| 1081 |
+
"step": 134
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.2159916926272065,
|
| 1085 |
+
"grad_norm": 0.12169156968593597,
|
| 1086 |
+
"learning_rate": 4.8454783398062106e-05,
|
| 1087 |
+
"loss": 0.2439,
|
| 1088 |
+
"num_input_tokens_seen": 9849528,
|
| 1089 |
+
"step": 135
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.232606438213915,
|
| 1093 |
+
"grad_norm": 0.11766713112592697,
|
| 1094 |
+
"learning_rate": 4.843204973729729e-05,
|
| 1095 |
+
"loss": 0.2538,
|
| 1096 |
+
"num_input_tokens_seen": 9931080,
|
| 1097 |
+
"step": 136
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.249221183800623,
|
| 1101 |
+
"grad_norm": 0.11854218691587448,
|
| 1102 |
+
"learning_rate": 4.840915547588725e-05,
|
| 1103 |
+
"loss": 0.2782,
|
| 1104 |
+
"num_input_tokens_seen": 10011176,
|
| 1105 |
+
"step": 137
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 2.265835929387331,
|
| 1109 |
+
"grad_norm": 0.1340581178665161,
|
| 1110 |
+
"learning_rate": 4.838610077074669e-05,
|
| 1111 |
+
"loss": 0.248,
|
| 1112 |
+
"num_input_tokens_seen": 10084128,
|
| 1113 |
+
"step": 138
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.2824506749740396,
|
| 1117 |
+
"grad_norm": 0.12075436115264893,
|
| 1118 |
+
"learning_rate": 4.836288577988996e-05,
|
| 1119 |
+
"loss": 0.2582,
|
| 1120 |
+
"num_input_tokens_seen": 10155536,
|
| 1121 |
+
"step": 139
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 2.2990654205607477,
|
| 1125 |
+
"grad_norm": 0.10599923878908157,
|
| 1126 |
+
"learning_rate": 4.8339510662430046e-05,
|
| 1127 |
+
"loss": 0.2199,
|
| 1128 |
+
"num_input_tokens_seen": 10251160,
|
| 1129 |
+
"step": 140
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.3156801661474558,
|
| 1133 |
+
"grad_norm": 0.1117846742272377,
|
| 1134 |
+
"learning_rate": 4.8315975578577355e-05,
|
| 1135 |
+
"loss": 0.2324,
|
| 1136 |
+
"num_input_tokens_seen": 10345864,
|
| 1137 |
+
"step": 141
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.3322949117341643,
|
| 1141 |
+
"grad_norm": 0.13972057402133942,
|
| 1142 |
+
"learning_rate": 4.8292280689638725e-05,
|
| 1143 |
+
"loss": 0.4072,
|
| 1144 |
+
"num_input_tokens_seen": 10417616,
|
| 1145 |
+
"step": 142
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.3489096573208723,
|
| 1149 |
+
"grad_norm": 0.13837860524654388,
|
| 1150 |
+
"learning_rate": 4.826842615801628e-05,
|
| 1151 |
+
"loss": 0.2607,
|
| 1152 |
+
"num_input_tokens_seen": 10481816,
|
| 1153 |
+
"step": 143
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.3655244029075804,
|
| 1157 |
+
"grad_norm": 0.14040137827396393,
|
| 1158 |
+
"learning_rate": 4.8244412147206284e-05,
|
| 1159 |
+
"loss": 0.3094,
|
| 1160 |
+
"num_input_tokens_seen": 10562056,
|
| 1161 |
+
"step": 144
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.382139148494289,
|
| 1165 |
+
"grad_norm": 0.1393299251794815,
|
| 1166 |
+
"learning_rate": 4.822023882179811e-05,
|
| 1167 |
+
"loss": 0.2407,
|
| 1168 |
+
"num_input_tokens_seen": 10612808,
|
| 1169 |
+
"step": 145
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 2.398753894080997,
|
| 1173 |
+
"grad_norm": 0.13878698647022247,
|
| 1174 |
+
"learning_rate": 4.8195906347473e-05,
|
| 1175 |
+
"loss": 0.2481,
|
| 1176 |
+
"num_input_tokens_seen": 10682328,
|
| 1177 |
+
"step": 146
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.415368639667705,
|
| 1181 |
+
"grad_norm": 0.10430227965116501,
|
| 1182 |
+
"learning_rate": 4.817141489100302e-05,
|
| 1183 |
+
"loss": 0.2528,
|
| 1184 |
+
"num_input_tokens_seen": 10771912,
|
| 1185 |
+
"step": 147
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.431983385254413,
|
| 1189 |
+
"grad_norm": 0.12963703274726868,
|
| 1190 |
+
"learning_rate": 4.814676462024988e-05,
|
| 1191 |
+
"loss": 0.2739,
|
| 1192 |
+
"num_input_tokens_seen": 10842232,
|
| 1193 |
+
"step": 148
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.4485981308411215,
|
| 1197 |
+
"grad_norm": 0.13274963200092316,
|
| 1198 |
+
"learning_rate": 4.8121955704163745e-05,
|
| 1199 |
+
"loss": 0.2407,
|
| 1200 |
+
"num_input_tokens_seen": 10902264,
|
| 1201 |
+
"step": 149
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.4652128764278296,
|
| 1205 |
+
"grad_norm": 0.11079717427492142,
|
| 1206 |
+
"learning_rate": 4.8096988312782174e-05,
|
| 1207 |
+
"loss": 0.2142,
|
| 1208 |
+
"num_input_tokens_seen": 10992744,
|
| 1209 |
+
"step": 150
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.4818276220145377,
|
| 1213 |
+
"grad_norm": 0.08429212868213654,
|
| 1214 |
+
"learning_rate": 4.8071862617228855e-05,
|
| 1215 |
+
"loss": 0.1428,
|
| 1216 |
+
"num_input_tokens_seen": 11090064,
|
| 1217 |
+
"step": 151
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 2.498442367601246,
|
| 1221 |
+
"grad_norm": 0.12903761863708496,
|
| 1222 |
+
"learning_rate": 4.8046578789712515e-05,
|
| 1223 |
+
"loss": 0.2268,
|
| 1224 |
+
"num_input_tokens_seen": 11162864,
|
| 1225 |
+
"step": 152
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 2.515057113187954,
|
| 1229 |
+
"grad_norm": 0.14638672769069672,
|
| 1230 |
+
"learning_rate": 4.8021137003525664e-05,
|
| 1231 |
+
"loss": 0.2388,
|
| 1232 |
+
"num_input_tokens_seen": 11224368,
|
| 1233 |
+
"step": 153
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.5316718587746623,
|
| 1237 |
+
"grad_norm": 0.1372838169336319,
|
| 1238 |
+
"learning_rate": 4.7995537433043446e-05,
|
| 1239 |
+
"loss": 0.2588,
|
| 1240 |
+
"num_input_tokens_seen": 11291056,
|
| 1241 |
+
"step": 154
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.5482866043613708,
|
| 1245 |
+
"grad_norm": 0.15665481984615326,
|
| 1246 |
+
"learning_rate": 4.796978025372246e-05,
|
| 1247 |
+
"loss": 0.2225,
|
| 1248 |
+
"num_input_tokens_seen": 11345464,
|
| 1249 |
+
"step": 155
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.564901349948079,
|
| 1253 |
+
"grad_norm": 0.13234855234622955,
|
| 1254 |
+
"learning_rate": 4.794386564209953e-05,
|
| 1255 |
+
"loss": 0.275,
|
| 1256 |
+
"num_input_tokens_seen": 11418912,
|
| 1257 |
+
"step": 156
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.581516095534787,
|
| 1261 |
+
"grad_norm": 0.13585953414440155,
|
| 1262 |
+
"learning_rate": 4.79177937757905e-05,
|
| 1263 |
+
"loss": 0.2407,
|
| 1264 |
+
"num_input_tokens_seen": 11491216,
|
| 1265 |
+
"step": 157
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 2.5981308411214954,
|
| 1269 |
+
"grad_norm": 0.1423913538455963,
|
| 1270 |
+
"learning_rate": 4.7891564833489035e-05,
|
| 1271 |
+
"loss": 0.1971,
|
| 1272 |
+
"num_input_tokens_seen": 11558016,
|
| 1273 |
+
"step": 158
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.6147455867082035,
|
| 1277 |
+
"grad_norm": 0.13013511896133423,
|
| 1278 |
+
"learning_rate": 4.7865178994965344e-05,
|
| 1279 |
+
"loss": 0.2362,
|
| 1280 |
+
"num_input_tokens_seen": 11630432,
|
| 1281 |
+
"step": 159
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.6313603322949115,
|
| 1285 |
+
"grad_norm": 0.1587141752243042,
|
| 1286 |
+
"learning_rate": 4.783863644106502e-05,
|
| 1287 |
+
"loss": 0.2252,
|
| 1288 |
+
"num_input_tokens_seen": 11684624,
|
| 1289 |
+
"step": 160
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.64797507788162,
|
| 1293 |
+
"grad_norm": 0.12592960894107819,
|
| 1294 |
+
"learning_rate": 4.781193735370777e-05,
|
| 1295 |
+
"loss": 0.2506,
|
| 1296 |
+
"num_input_tokens_seen": 11770232,
|
| 1297 |
+
"step": 161
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.664589823468328,
|
| 1301 |
+
"grad_norm": 0.1583249419927597,
|
| 1302 |
+
"learning_rate": 4.7785081915886134e-05,
|
| 1303 |
+
"loss": 0.2352,
|
| 1304 |
+
"num_input_tokens_seen": 11828360,
|
| 1305 |
+
"step": 162
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.681204569055036,
|
| 1309 |
+
"grad_norm": 0.14881783723831177,
|
| 1310 |
+
"learning_rate": 4.775807031166428e-05,
|
| 1311 |
+
"loss": 0.2308,
|
| 1312 |
+
"num_input_tokens_seen": 11915944,
|
| 1313 |
+
"step": 163
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.6978193146417446,
|
| 1317 |
+
"grad_norm": 0.1607823222875595,
|
| 1318 |
+
"learning_rate": 4.773090272617672e-05,
|
| 1319 |
+
"loss": 0.2238,
|
| 1320 |
+
"num_input_tokens_seen": 11981792,
|
| 1321 |
+
"step": 164
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.7144340602284527,
|
| 1325 |
+
"grad_norm": 0.13583113253116608,
|
| 1326 |
+
"learning_rate": 4.7703579345627035e-05,
|
| 1327 |
+
"loss": 0.3196,
|
| 1328 |
+
"num_input_tokens_seen": 12044024,
|
| 1329 |
+
"step": 165
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.7310488058151607,
|
| 1333 |
+
"grad_norm": 0.19167298078536987,
|
| 1334 |
+
"learning_rate": 4.7676100357286624e-05,
|
| 1335 |
+
"loss": 0.2745,
|
| 1336 |
+
"num_input_tokens_seen": 12093424,
|
| 1337 |
+
"step": 166
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 2.7476635514018692,
|
| 1341 |
+
"grad_norm": 0.130703404545784,
|
| 1342 |
+
"learning_rate": 4.76484659494934e-05,
|
| 1343 |
+
"loss": 0.2285,
|
| 1344 |
+
"num_input_tokens_seen": 12167792,
|
| 1345 |
+
"step": 167
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 2.7642782969885773,
|
| 1349 |
+
"grad_norm": 0.14331185817718506,
|
| 1350 |
+
"learning_rate": 4.762067631165049e-05,
|
| 1351 |
+
"loss": 0.2506,
|
| 1352 |
+
"num_input_tokens_seen": 12233712,
|
| 1353 |
+
"step": 168
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.7808930425752854,
|
| 1357 |
+
"grad_norm": 0.12700341641902924,
|
| 1358 |
+
"learning_rate": 4.7592731634224966e-05,
|
| 1359 |
+
"loss": 0.2052,
|
| 1360 |
+
"num_input_tokens_seen": 12310544,
|
| 1361 |
+
"step": 169
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.797507788161994,
|
| 1365 |
+
"grad_norm": 0.15118420124053955,
|
| 1366 |
+
"learning_rate": 4.756463210874652e-05,
|
| 1367 |
+
"loss": 0.2309,
|
| 1368 |
+
"num_input_tokens_seen": 12400160,
|
| 1369 |
+
"step": 170
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.814122533748702,
|
| 1373 |
+
"grad_norm": 0.14001020789146423,
|
| 1374 |
+
"learning_rate": 4.753637792780614e-05,
|
| 1375 |
+
"loss": 0.2544,
|
| 1376 |
+
"num_input_tokens_seen": 12480432,
|
| 1377 |
+
"step": 171
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.83073727933541,
|
| 1381 |
+
"grad_norm": 0.12076311558485031,
|
| 1382 |
+
"learning_rate": 4.7507969285054845e-05,
|
| 1383 |
+
"loss": 0.2434,
|
| 1384 |
+
"num_input_tokens_seen": 12568064,
|
| 1385 |
+
"step": 172
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.8473520249221185,
|
| 1389 |
+
"grad_norm": 0.16462342441082,
|
| 1390 |
+
"learning_rate": 4.7479406375202264e-05,
|
| 1391 |
+
"loss": 0.2417,
|
| 1392 |
+
"num_input_tokens_seen": 12647400,
|
| 1393 |
+
"step": 173
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 2.8639667705088265,
|
| 1397 |
+
"grad_norm": 0.17294971644878387,
|
| 1398 |
+
"learning_rate": 4.745068939401539e-05,
|
| 1399 |
+
"loss": 0.2121,
|
| 1400 |
+
"num_input_tokens_seen": 12698208,
|
| 1401 |
+
"step": 174
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 2.8805815160955346,
|
| 1405 |
+
"grad_norm": 0.16743803024291992,
|
| 1406 |
+
"learning_rate": 4.742181853831721e-05,
|
| 1407 |
+
"loss": 0.2238,
|
| 1408 |
+
"num_input_tokens_seen": 12758528,
|
| 1409 |
+
"step": 175
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.897196261682243,
|
| 1413 |
+
"grad_norm": 0.14583320915699005,
|
| 1414 |
+
"learning_rate": 4.7392794005985326e-05,
|
| 1415 |
+
"loss": 0.2333,
|
| 1416 |
+
"num_input_tokens_seen": 12837264,
|
| 1417 |
+
"step": 176
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.913811007268951,
|
| 1421 |
+
"grad_norm": 0.1509270817041397,
|
| 1422 |
+
"learning_rate": 4.7363615995950626e-05,
|
| 1423 |
+
"loss": 0.2179,
|
| 1424 |
+
"num_input_tokens_seen": 12902368,
|
| 1425 |
+
"step": 177
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.930425752855659,
|
| 1429 |
+
"grad_norm": 0.12910738587379456,
|
| 1430 |
+
"learning_rate": 4.733428470819594e-05,
|
| 1431 |
+
"loss": 0.2144,
|
| 1432 |
+
"num_input_tokens_seen": 12974296,
|
| 1433 |
+
"step": 178
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 2.9470404984423677,
|
| 1437 |
+
"grad_norm": 0.142000213265419,
|
| 1438 |
+
"learning_rate": 4.730480034375462e-05,
|
| 1439 |
+
"loss": 0.2413,
|
| 1440 |
+
"num_input_tokens_seen": 13057280,
|
| 1441 |
+
"step": 179
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.9636552440290758,
|
| 1445 |
+
"grad_norm": 0.131468266248703,
|
| 1446 |
+
"learning_rate": 4.72751631047092e-05,
|
| 1447 |
+
"loss": 0.294,
|
| 1448 |
+
"num_input_tokens_seen": 13158232,
|
| 1449 |
+
"step": 180
|
| 1450 |
+
}
|
| 1451 |
+
],
|
| 1452 |
+
"logging_steps": 1.0,
|
| 1453 |
+
"max_steps": 1200,
|
| 1454 |
+
"num_input_tokens_seen": 13158232,
|
| 1455 |
+
"num_train_epochs": 20,
|
| 1456 |
+
"save_steps": 60,
|
| 1457 |
+
"stateful_callbacks": {
|
| 1458 |
+
"TrainerControl": {
|
| 1459 |
+
"args": {
|
| 1460 |
+
"should_epoch_stop": false,
|
| 1461 |
+
"should_evaluate": false,
|
| 1462 |
+
"should_log": false,
|
| 1463 |
+
"should_save": true,
|
| 1464 |
+
"should_training_stop": false
|
| 1465 |
+
},
|
| 1466 |
+
"attributes": {}
|
| 1467 |
+
}
|
| 1468 |
+
},
|
| 1469 |
+
"total_flos": 1.1100504584051753e+18,
|
| 1470 |
+
"train_batch_size": 1,
|
| 1471 |
+
"trial_name": null,
|
| 1472 |
+
"trial_params": null
|
| 1473 |
+
}
|
checkpoint-180/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ead4a6550d360b2767d5cafb708fc1265f2158252d104b64f05a5368cafaafc9
|
| 3 |
+
size 5752
|
checkpoint-180/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-240/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:307b9f6a493fb470266b92a5409659861bb2745a1b7b02c05eeb7de263283265
|
| 3 |
+
size 275341720
|
checkpoint-240/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-240/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e62068bdff9b5621b6e7e53cf7370e9e2884050edc6dd43bfcb95a634ccb0399
|
| 3 |
+
size 14512
|
checkpoint-240/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a006ff9e7b7399f64c2a6f6393050f76d64d53d7deed71eb47af5fe5b9129ff0
|
| 3 |
+
size 14512
|
checkpoint-240/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3de8199cf9d6d12153e18123cf96dc2b84397b2c8e869fab2d188b1c5614bc21
|
| 3 |
+
size 1064
|
checkpoint-240/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-240/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-240/tokenizer_config.json
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 17500,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"padding_side": "right",
|
| 206 |
+
"split_special_tokens": false,
|
| 207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
+
"unk_token": null
|
| 209 |
+
}
|
checkpoint-240/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ead4a6550d360b2767d5cafb708fc1265f2158252d104b64f05a5368cafaafc9
|
| 3 |
+
size 5752
|
checkpoint-240/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81df82e1c1ea0593dc955bf2da5a08d2263eef78561fa5756619ad10cf4daa0b
|
| 3 |
+
size 275341720
|
checkpoint-300/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:119e76ebf22a0e33b3c8ac2037a01ed4890484f8995a2ec9693ec9d2e0d014e6
|
| 3 |
+
size 551070514
|
checkpoint-300/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a18b49e519667868d0736ec87403aa4bf9e908cb2951191cdf0a78384ae9104
|
| 3 |
+
size 14512
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:689b990854a80fc73dcc5a64e399a29756446d186497e777a92412637572ce18
|
| 3 |
+
size 1064
|
checkpoint-300/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,2433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.930425752855659,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016614745586708203,
|
| 13 |
+
"grad_norm": 0.050998032093048096,
|
| 14 |
+
"learning_rate": 4.999991432639962e-05,
|
| 15 |
+
"loss": 0.5487,
|
| 16 |
+
"num_input_tokens_seen": 70408,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.033229491173416406,
|
| 21 |
+
"grad_norm": 0.049370743334293365,
|
| 22 |
+
"learning_rate": 4.999965730618567e-05,
|
| 23 |
+
"loss": 0.4981,
|
| 24 |
+
"num_input_tokens_seen": 139640,
|
| 25 |
+
"step": 2
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.04984423676012461,
|
| 29 |
+
"grad_norm": 0.05077400803565979,
|
| 30 |
+
"learning_rate": 4.9999228941119745e-05,
|
| 31 |
+
"loss": 0.5505,
|
| 32 |
+
"num_input_tokens_seen": 223656,
|
| 33 |
+
"step": 3
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06645898234683281,
|
| 37 |
+
"grad_norm": 0.04397282376885414,
|
| 38 |
+
"learning_rate": 4.999862923413781e-05,
|
| 39 |
+
"loss": 0.504,
|
| 40 |
+
"num_input_tokens_seen": 300688,
|
| 41 |
+
"step": 4
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.08307372793354102,
|
| 45 |
+
"grad_norm": 0.05225864797830582,
|
| 46 |
+
"learning_rate": 4.999785818935018e-05,
|
| 47 |
+
"loss": 0.4925,
|
| 48 |
+
"num_input_tokens_seen": 366368,
|
| 49 |
+
"step": 5
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.09968847352024922,
|
| 53 |
+
"grad_norm": 0.049482282251119614,
|
| 54 |
+
"learning_rate": 4.999691581204152e-05,
|
| 55 |
+
"loss": 0.4771,
|
| 56 |
+
"num_input_tokens_seen": 445808,
|
| 57 |
+
"step": 6
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.11630321910695743,
|
| 61 |
+
"grad_norm": 0.05594080314040184,
|
| 62 |
+
"learning_rate": 4.9995802108670775e-05,
|
| 63 |
+
"loss": 0.4986,
|
| 64 |
+
"num_input_tokens_seen": 522800,
|
| 65 |
+
"step": 7
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13291796469366562,
|
| 69 |
+
"grad_norm": 0.051852282136678696,
|
| 70 |
+
"learning_rate": 4.999451708687114e-05,
|
| 71 |
+
"loss": 0.5171,
|
| 72 |
+
"num_input_tokens_seen": 599608,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.14953271028037382,
|
| 77 |
+
"grad_norm": 0.045517683029174805,
|
| 78 |
+
"learning_rate": 4.9993060755450015e-05,
|
| 79 |
+
"loss": 0.5669,
|
| 80 |
+
"num_input_tokens_seen": 681424,
|
| 81 |
+
"step": 9
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.16614745586708204,
|
| 85 |
+
"grad_norm": 0.044325754046440125,
|
| 86 |
+
"learning_rate": 4.999143312438893e-05,
|
| 87 |
+
"loss": 0.4218,
|
| 88 |
+
"num_input_tokens_seen": 756744,
|
| 89 |
+
"step": 10
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.18276220145379024,
|
| 93 |
+
"grad_norm": 0.04328459873795509,
|
| 94 |
+
"learning_rate": 4.998963420484349e-05,
|
| 95 |
+
"loss": 0.434,
|
| 96 |
+
"num_input_tokens_seen": 842576,
|
| 97 |
+
"step": 11
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.19937694704049844,
|
| 101 |
+
"grad_norm": 0.04725787043571472,
|
| 102 |
+
"learning_rate": 4.998766400914329e-05,
|
| 103 |
+
"loss": 0.4287,
|
| 104 |
+
"num_input_tokens_seen": 917232,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.21599169262720663,
|
| 109 |
+
"grad_norm": 0.03806879371404648,
|
| 110 |
+
"learning_rate": 4.9985522550791825e-05,
|
| 111 |
+
"loss": 0.3454,
|
| 112 |
+
"num_input_tokens_seen": 1006800,
|
| 113 |
+
"step": 13
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.23260643821391486,
|
| 117 |
+
"grad_norm": 0.05201176926493645,
|
| 118 |
+
"learning_rate": 4.998320984446641e-05,
|
| 119 |
+
"loss": 0.436,
|
| 120 |
+
"num_input_tokens_seen": 1085824,
|
| 121 |
+
"step": 14
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.24922118380062305,
|
| 125 |
+
"grad_norm": 0.047955628484487534,
|
| 126 |
+
"learning_rate": 4.9980725906018074e-05,
|
| 127 |
+
"loss": 0.4625,
|
| 128 |
+
"num_input_tokens_seen": 1164160,
|
| 129 |
+
"step": 15
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.26583592938733125,
|
| 133 |
+
"grad_norm": 0.05529098957777023,
|
| 134 |
+
"learning_rate": 4.997807075247146e-05,
|
| 135 |
+
"loss": 0.5035,
|
| 136 |
+
"num_input_tokens_seen": 1242264,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.2824506749740395,
|
| 141 |
+
"grad_norm": 0.04751162976026535,
|
| 142 |
+
"learning_rate": 4.997524440202469e-05,
|
| 143 |
+
"loss": 0.4354,
|
| 144 |
+
"num_input_tokens_seen": 1325904,
|
| 145 |
+
"step": 17
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.29906542056074764,
|
| 149 |
+
"grad_norm": 0.06726882606744766,
|
| 150 |
+
"learning_rate": 4.9972246874049254e-05,
|
| 151 |
+
"loss": 0.5439,
|
| 152 |
+
"num_input_tokens_seen": 1385632,
|
| 153 |
+
"step": 18
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.31568016614745587,
|
| 157 |
+
"grad_norm": 0.05245920270681381,
|
| 158 |
+
"learning_rate": 4.996907818908987e-05,
|
| 159 |
+
"loss": 0.3727,
|
| 160 |
+
"num_input_tokens_seen": 1470632,
|
| 161 |
+
"step": 19
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.3322949117341641,
|
| 165 |
+
"grad_norm": 0.05745376646518707,
|
| 166 |
+
"learning_rate": 4.996573836886435e-05,
|
| 167 |
+
"loss": 0.4894,
|
| 168 |
+
"num_input_tokens_seen": 1547536,
|
| 169 |
+
"step": 20
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.34890965732087226,
|
| 173 |
+
"grad_norm": 0.056607529520988464,
|
| 174 |
+
"learning_rate": 4.9962227436263453e-05,
|
| 175 |
+
"loss": 0.3846,
|
| 176 |
+
"num_input_tokens_seen": 1615528,
|
| 177 |
+
"step": 21
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3655244029075805,
|
| 181 |
+
"grad_norm": 0.06150667741894722,
|
| 182 |
+
"learning_rate": 4.995854541535071e-05,
|
| 183 |
+
"loss": 0.4362,
|
| 184 |
+
"num_input_tokens_seen": 1694352,
|
| 185 |
+
"step": 22
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3821391484942887,
|
| 189 |
+
"grad_norm": 0.056484442204236984,
|
| 190 |
+
"learning_rate": 4.9954692331362294e-05,
|
| 191 |
+
"loss": 0.4438,
|
| 192 |
+
"num_input_tokens_seen": 1753776,
|
| 193 |
+
"step": 23
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.3987538940809969,
|
| 197 |
+
"grad_norm": 0.0704159140586853,
|
| 198 |
+
"learning_rate": 4.995066821070679e-05,
|
| 199 |
+
"loss": 0.4496,
|
| 200 |
+
"num_input_tokens_seen": 1809048,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.4153686396677051,
|
| 205 |
+
"grad_norm": 0.06202029809355736,
|
| 206 |
+
"learning_rate": 4.994647308096509e-05,
|
| 207 |
+
"loss": 0.5096,
|
| 208 |
+
"num_input_tokens_seen": 1884264,
|
| 209 |
+
"step": 25
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.43198338525441327,
|
| 213 |
+
"grad_norm": 0.04237145930528641,
|
| 214 |
+
"learning_rate": 4.994210697089014e-05,
|
| 215 |
+
"loss": 0.3722,
|
| 216 |
+
"num_input_tokens_seen": 1981704,
|
| 217 |
+
"step": 26
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.4485981308411215,
|
| 221 |
+
"grad_norm": 0.06920398026704788,
|
| 222 |
+
"learning_rate": 4.9937569910406756e-05,
|
| 223 |
+
"loss": 0.4103,
|
| 224 |
+
"num_input_tokens_seen": 2044144,
|
| 225 |
+
"step": 27
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.4652128764278297,
|
| 229 |
+
"grad_norm": 0.062432270497083664,
|
| 230 |
+
"learning_rate": 4.9932861930611454e-05,
|
| 231 |
+
"loss": 0.357,
|
| 232 |
+
"num_input_tokens_seen": 2107584,
|
| 233 |
+
"step": 28
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4818276220145379,
|
| 237 |
+
"grad_norm": 0.06791180372238159,
|
| 238 |
+
"learning_rate": 4.9927983063772196e-05,
|
| 239 |
+
"loss": 0.3889,
|
| 240 |
+
"num_input_tokens_seen": 2169248,
|
| 241 |
+
"step": 29
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4984423676012461,
|
| 245 |
+
"grad_norm": 0.07219590991735458,
|
| 246 |
+
"learning_rate": 4.99229333433282e-05,
|
| 247 |
+
"loss": 0.3543,
|
| 248 |
+
"num_input_tokens_seen": 2230344,
|
| 249 |
+
"step": 30
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.5150571131879543,
|
| 253 |
+
"grad_norm": 0.0647474005818367,
|
| 254 |
+
"learning_rate": 4.9917712803889674e-05,
|
| 255 |
+
"loss": 0.3453,
|
| 256 |
+
"num_input_tokens_seen": 2302368,
|
| 257 |
+
"step": 31
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.5316718587746625,
|
| 261 |
+
"grad_norm": 0.07434642314910889,
|
| 262 |
+
"learning_rate": 4.991232148123761e-05,
|
| 263 |
+
"loss": 0.435,
|
| 264 |
+
"num_input_tokens_seen": 2369984,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.5482866043613707,
|
| 269 |
+
"grad_norm": 0.05302443355321884,
|
| 270 |
+
"learning_rate": 4.990675941232353e-05,
|
| 271 |
+
"loss": 0.3981,
|
| 272 |
+
"num_input_tokens_seen": 2453032,
|
| 273 |
+
"step": 33
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.564901349948079,
|
| 277 |
+
"grad_norm": 0.053745292127132416,
|
| 278 |
+
"learning_rate": 4.990102663526924e-05,
|
| 279 |
+
"loss": 0.3755,
|
| 280 |
+
"num_input_tokens_seen": 2527464,
|
| 281 |
+
"step": 34
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.5815160955347871,
|
| 285 |
+
"grad_norm": 0.06717613339424133,
|
| 286 |
+
"learning_rate": 4.989512318936655e-05,
|
| 287 |
+
"loss": 0.3699,
|
| 288 |
+
"num_input_tokens_seen": 2597032,
|
| 289 |
+
"step": 35
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5981308411214953,
|
| 293 |
+
"grad_norm": 0.071847103536129,
|
| 294 |
+
"learning_rate": 4.9889049115077005e-05,
|
| 295 |
+
"loss": 0.3705,
|
| 296 |
+
"num_input_tokens_seen": 2671704,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.6147455867082036,
|
| 301 |
+
"grad_norm": 0.0460306741297245,
|
| 302 |
+
"learning_rate": 4.988280445403164e-05,
|
| 303 |
+
"loss": 0.3797,
|
| 304 |
+
"num_input_tokens_seen": 2767640,
|
| 305 |
+
"step": 37
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.6313603322949117,
|
| 309 |
+
"grad_norm": 0.053273387253284454,
|
| 310 |
+
"learning_rate": 4.987638924903067e-05,
|
| 311 |
+
"loss": 0.3799,
|
| 312 |
+
"num_input_tokens_seen": 2843720,
|
| 313 |
+
"step": 38
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.6479750778816199,
|
| 317 |
+
"grad_norm": 0.05600422993302345,
|
| 318 |
+
"learning_rate": 4.9869803544043166e-05,
|
| 319 |
+
"loss": 0.2866,
|
| 320 |
+
"num_input_tokens_seen": 2921472,
|
| 321 |
+
"step": 39
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.6645898234683282,
|
| 325 |
+
"grad_norm": 0.06414052098989487,
|
| 326 |
+
"learning_rate": 4.9863047384206835e-05,
|
| 327 |
+
"loss": 0.4115,
|
| 328 |
+
"num_input_tokens_seen": 2998400,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.6812045690550363,
|
| 333 |
+
"grad_norm": 0.09214208275079727,
|
| 334 |
+
"learning_rate": 4.985612081582764e-05,
|
| 335 |
+
"loss": 0.3804,
|
| 336 |
+
"num_input_tokens_seen": 3059648,
|
| 337 |
+
"step": 41
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.6978193146417445,
|
| 341 |
+
"grad_norm": 0.0555964931845665,
|
| 342 |
+
"learning_rate": 4.98490238863795e-05,
|
| 343 |
+
"loss": 0.3121,
|
| 344 |
+
"num_input_tokens_seen": 3140184,
|
| 345 |
+
"step": 42
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7144340602284528,
|
| 349 |
+
"grad_norm": 0.06256969273090363,
|
| 350 |
+
"learning_rate": 4.984175664450397e-05,
|
| 351 |
+
"loss": 0.3271,
|
| 352 |
+
"num_input_tokens_seen": 3207184,
|
| 353 |
+
"step": 43
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.731048805815161,
|
| 357 |
+
"grad_norm": 0.0543232187628746,
|
| 358 |
+
"learning_rate": 4.983431914000991e-05,
|
| 359 |
+
"loss": 0.364,
|
| 360 |
+
"num_input_tokens_seen": 3292344,
|
| 361 |
+
"step": 44
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.7476635514018691,
|
| 365 |
+
"grad_norm": 0.06077824532985687,
|
| 366 |
+
"learning_rate": 4.982671142387316e-05,
|
| 367 |
+
"loss": 0.3894,
|
| 368 |
+
"num_input_tokens_seen": 3365384,
|
| 369 |
+
"step": 45
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.7642782969885774,
|
| 373 |
+
"grad_norm": 0.06091070920228958,
|
| 374 |
+
"learning_rate": 4.981893354823614e-05,
|
| 375 |
+
"loss": 0.3354,
|
| 376 |
+
"num_input_tokens_seen": 3440720,
|
| 377 |
+
"step": 46
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.7808930425752856,
|
| 381 |
+
"grad_norm": 0.054153311997652054,
|
| 382 |
+
"learning_rate": 4.9810985566407544e-05,
|
| 383 |
+
"loss": 0.3058,
|
| 384 |
+
"num_input_tokens_seen": 3533576,
|
| 385 |
+
"step": 47
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.7975077881619937,
|
| 389 |
+
"grad_norm": 0.06662417948246002,
|
| 390 |
+
"learning_rate": 4.980286753286195e-05,
|
| 391 |
+
"loss": 0.4658,
|
| 392 |
+
"num_input_tokens_seen": 3599744,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.814122533748702,
|
| 397 |
+
"grad_norm": 0.05790851265192032,
|
| 398 |
+
"learning_rate": 4.979457950323945e-05,
|
| 399 |
+
"loss": 0.3647,
|
| 400 |
+
"num_input_tokens_seen": 3689520,
|
| 401 |
+
"step": 49
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8307372793354102,
|
| 405 |
+
"grad_norm": 0.10742159187793732,
|
| 406 |
+
"learning_rate": 4.9786121534345265e-05,
|
| 407 |
+
"loss": 0.343,
|
| 408 |
+
"num_input_tokens_seen": 3751808,
|
| 409 |
+
"step": 50
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.8473520249221184,
|
| 413 |
+
"grad_norm": 0.05565556138753891,
|
| 414 |
+
"learning_rate": 4.9777493684149375e-05,
|
| 415 |
+
"loss": 0.3317,
|
| 416 |
+
"num_input_tokens_seen": 3839096,
|
| 417 |
+
"step": 51
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.8639667705088265,
|
| 421 |
+
"grad_norm": 0.05752381682395935,
|
| 422 |
+
"learning_rate": 4.976869601178609e-05,
|
| 423 |
+
"loss": 0.38,
|
| 424 |
+
"num_input_tokens_seen": 3919824,
|
| 425 |
+
"step": 52
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.8805815160955348,
|
| 429 |
+
"grad_norm": 0.06406434625387192,
|
| 430 |
+
"learning_rate": 4.975972857755369e-05,
|
| 431 |
+
"loss": 0.2676,
|
| 432 |
+
"num_input_tokens_seen": 3989312,
|
| 433 |
+
"step": 53
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.897196261682243,
|
| 437 |
+
"grad_norm": 0.0653691440820694,
|
| 438 |
+
"learning_rate": 4.975059144291394e-05,
|
| 439 |
+
"loss": 0.3516,
|
| 440 |
+
"num_input_tokens_seen": 4060528,
|
| 441 |
+
"step": 54
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.9138110072689511,
|
| 445 |
+
"grad_norm": 0.06272953748703003,
|
| 446 |
+
"learning_rate": 4.974128467049176e-05,
|
| 447 |
+
"loss": 0.3004,
|
| 448 |
+
"num_input_tokens_seen": 4129368,
|
| 449 |
+
"step": 55
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.9304257528556594,
|
| 453 |
+
"grad_norm": 0.08054930716753006,
|
| 454 |
+
"learning_rate": 4.9731808324074717e-05,
|
| 455 |
+
"loss": 0.3009,
|
| 456 |
+
"num_input_tokens_seen": 4175208,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9470404984423676,
|
| 461 |
+
"grad_norm": 0.07523038238286972,
|
| 462 |
+
"learning_rate": 4.972216246861262e-05,
|
| 463 |
+
"loss": 0.2814,
|
| 464 |
+
"num_input_tokens_seen": 4218096,
|
| 465 |
+
"step": 57
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.9636552440290758,
|
| 469 |
+
"grad_norm": 0.07347433269023895,
|
| 470 |
+
"learning_rate": 4.971234717021709e-05,
|
| 471 |
+
"loss": 0.3321,
|
| 472 |
+
"num_input_tokens_seen": 4275968,
|
| 473 |
+
"step": 58
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.980269989615784,
|
| 477 |
+
"grad_norm": 0.05830248445272446,
|
| 478 |
+
"learning_rate": 4.9702362496161085e-05,
|
| 479 |
+
"loss": 0.2881,
|
| 480 |
+
"num_input_tokens_seen": 4346616,
|
| 481 |
+
"step": 59
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.9968847352024922,
|
| 485 |
+
"grad_norm": 0.061629410833120346,
|
| 486 |
+
"learning_rate": 4.9692208514878444e-05,
|
| 487 |
+
"loss": 0.2993,
|
| 488 |
+
"num_input_tokens_seen": 4425064,
|
| 489 |
+
"step": 60
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.0,
|
| 493 |
+
"grad_norm": 0.13380740582942963,
|
| 494 |
+
"learning_rate": 4.968188529596342e-05,
|
| 495 |
+
"loss": 0.2511,
|
| 496 |
+
"num_input_tokens_seen": 4435328,
|
| 497 |
+
"step": 61
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.0166147455867083,
|
| 501 |
+
"grad_norm": 0.0726238414645195,
|
| 502 |
+
"learning_rate": 4.9671392910170185e-05,
|
| 503 |
+
"loss": 0.3127,
|
| 504 |
+
"num_input_tokens_seen": 4500104,
|
| 505 |
+
"step": 62
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.0332294911734163,
|
| 509 |
+
"grad_norm": 0.05980083718895912,
|
| 510 |
+
"learning_rate": 4.966073142941239e-05,
|
| 511 |
+
"loss": 0.3601,
|
| 512 |
+
"num_input_tokens_seen": 4581976,
|
| 513 |
+
"step": 63
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.0498442367601246,
|
| 517 |
+
"grad_norm": 0.06445376574993134,
|
| 518 |
+
"learning_rate": 4.964990092676263e-05,
|
| 519 |
+
"loss": 0.3049,
|
| 520 |
+
"num_input_tokens_seen": 4652160,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.066458982346833,
|
| 525 |
+
"grad_norm": 0.07824505120515823,
|
| 526 |
+
"learning_rate": 4.9638901476451946e-05,
|
| 527 |
+
"loss": 0.3099,
|
| 528 |
+
"num_input_tokens_seen": 4709368,
|
| 529 |
+
"step": 65
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.083073727933541,
|
| 533 |
+
"grad_norm": 0.058268457651138306,
|
| 534 |
+
"learning_rate": 4.962773315386935e-05,
|
| 535 |
+
"loss": 0.3273,
|
| 536 |
+
"num_input_tokens_seen": 4798256,
|
| 537 |
+
"step": 66
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.0996884735202492,
|
| 541 |
+
"grad_norm": 0.07069691270589828,
|
| 542 |
+
"learning_rate": 4.961639603556127e-05,
|
| 543 |
+
"loss": 0.282,
|
| 544 |
+
"num_input_tokens_seen": 4859200,
|
| 545 |
+
"step": 67
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.1163032191069575,
|
| 549 |
+
"grad_norm": 0.0775996670126915,
|
| 550 |
+
"learning_rate": 4.960489019923105e-05,
|
| 551 |
+
"loss": 0.3642,
|
| 552 |
+
"num_input_tokens_seen": 4925992,
|
| 553 |
+
"step": 68
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.1329179646936656,
|
| 557 |
+
"grad_norm": 0.07044171541929245,
|
| 558 |
+
"learning_rate": 4.9593215723738404e-05,
|
| 559 |
+
"loss": 0.2896,
|
| 560 |
+
"num_input_tokens_seen": 4998808,
|
| 561 |
+
"step": 69
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.1495327102803738,
|
| 565 |
+
"grad_norm": 0.05971802771091461,
|
| 566 |
+
"learning_rate": 4.958137268909887e-05,
|
| 567 |
+
"loss": 0.2578,
|
| 568 |
+
"num_input_tokens_seen": 5089672,
|
| 569 |
+
"step": 70
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.1661474558670821,
|
| 573 |
+
"grad_norm": 0.07145556062459946,
|
| 574 |
+
"learning_rate": 4.9569361176483286e-05,
|
| 575 |
+
"loss": 0.3243,
|
| 576 |
+
"num_input_tokens_seen": 5166744,
|
| 577 |
+
"step": 71
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.1827622014537902,
|
| 581 |
+
"grad_norm": 0.07455787807703018,
|
| 582 |
+
"learning_rate": 4.9557181268217227e-05,
|
| 583 |
+
"loss": 0.3949,
|
| 584 |
+
"num_input_tokens_seen": 5228264,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.1993769470404985,
|
| 589 |
+
"grad_norm": 0.055582575500011444,
|
| 590 |
+
"learning_rate": 4.9544833047780394e-05,
|
| 591 |
+
"loss": 0.2877,
|
| 592 |
+
"num_input_tokens_seen": 5338224,
|
| 593 |
+
"step": 73
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.2159916926272065,
|
| 597 |
+
"grad_norm": 0.07675391435623169,
|
| 598 |
+
"learning_rate": 4.9532316599806124e-05,
|
| 599 |
+
"loss": 0.3152,
|
| 600 |
+
"num_input_tokens_seen": 5399848,
|
| 601 |
+
"step": 74
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.2326064382139148,
|
| 605 |
+
"grad_norm": 0.08048644661903381,
|
| 606 |
+
"learning_rate": 4.951963201008076e-05,
|
| 607 |
+
"loss": 0.2976,
|
| 608 |
+
"num_input_tokens_seen": 5468624,
|
| 609 |
+
"step": 75
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.249221183800623,
|
| 613 |
+
"grad_norm": 0.07579060643911362,
|
| 614 |
+
"learning_rate": 4.9506779365543046e-05,
|
| 615 |
+
"loss": 0.2982,
|
| 616 |
+
"num_input_tokens_seen": 5536776,
|
| 617 |
+
"step": 76
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.2658359293873311,
|
| 621 |
+
"grad_norm": 0.07828006893396378,
|
| 622 |
+
"learning_rate": 4.949375875428357e-05,
|
| 623 |
+
"loss": 0.3272,
|
| 624 |
+
"num_input_tokens_seen": 5609296,
|
| 625 |
+
"step": 77
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.2824506749740394,
|
| 629 |
+
"grad_norm": 0.08079098165035248,
|
| 630 |
+
"learning_rate": 4.9480570265544144e-05,
|
| 631 |
+
"loss": 0.2768,
|
| 632 |
+
"num_input_tokens_seen": 5663824,
|
| 633 |
+
"step": 78
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.2990654205607477,
|
| 637 |
+
"grad_norm": 0.07579358667135239,
|
| 638 |
+
"learning_rate": 4.94672139897172e-05,
|
| 639 |
+
"loss": 0.318,
|
| 640 |
+
"num_input_tokens_seen": 5742032,
|
| 641 |
+
"step": 79
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.3156801661474558,
|
| 645 |
+
"grad_norm": 0.07588379085063934,
|
| 646 |
+
"learning_rate": 4.9453690018345144e-05,
|
| 647 |
+
"loss": 0.3007,
|
| 648 |
+
"num_input_tokens_seen": 5816864,
|
| 649 |
+
"step": 80
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.332294911734164,
|
| 653 |
+
"grad_norm": 0.08709035068750381,
|
| 654 |
+
"learning_rate": 4.943999844411977e-05,
|
| 655 |
+
"loss": 0.2797,
|
| 656 |
+
"num_input_tokens_seen": 5881624,
|
| 657 |
+
"step": 81
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.3489096573208723,
|
| 661 |
+
"grad_norm": 0.05975884944200516,
|
| 662 |
+
"learning_rate": 4.94261393608816e-05,
|
| 663 |
+
"loss": 0.2591,
|
| 664 |
+
"num_input_tokens_seen": 5970272,
|
| 665 |
+
"step": 82
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.3655244029075804,
|
| 669 |
+
"grad_norm": 0.07372818142175674,
|
| 670 |
+
"learning_rate": 4.941211286361922e-05,
|
| 671 |
+
"loss": 0.2687,
|
| 672 |
+
"num_input_tokens_seen": 6058752,
|
| 673 |
+
"step": 83
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 1.3821391484942886,
|
| 677 |
+
"grad_norm": 0.09071576595306396,
|
| 678 |
+
"learning_rate": 4.939791904846869e-05,
|
| 679 |
+
"loss": 0.2979,
|
| 680 |
+
"num_input_tokens_seen": 6120064,
|
| 681 |
+
"step": 84
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.398753894080997,
|
| 685 |
+
"grad_norm": 0.0849960595369339,
|
| 686 |
+
"learning_rate": 4.938355801271282e-05,
|
| 687 |
+
"loss": 0.2927,
|
| 688 |
+
"num_input_tokens_seen": 6182072,
|
| 689 |
+
"step": 85
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.415368639667705,
|
| 693 |
+
"grad_norm": 0.08258760720491409,
|
| 694 |
+
"learning_rate": 4.936902985478055e-05,
|
| 695 |
+
"loss": 0.295,
|
| 696 |
+
"num_input_tokens_seen": 6269680,
|
| 697 |
+
"step": 86
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 1.4319833852544133,
|
| 701 |
+
"grad_norm": 0.0851503536105156,
|
| 702 |
+
"learning_rate": 4.935433467424624e-05,
|
| 703 |
+
"loss": 0.2925,
|
| 704 |
+
"num_input_tokens_seen": 6347424,
|
| 705 |
+
"step": 87
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.4485981308411215,
|
| 709 |
+
"grad_norm": 0.08852345496416092,
|
| 710 |
+
"learning_rate": 4.933947257182901e-05,
|
| 711 |
+
"loss": 0.3153,
|
| 712 |
+
"num_input_tokens_seen": 6412584,
|
| 713 |
+
"step": 88
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.4652128764278296,
|
| 717 |
+
"grad_norm": 0.08184897154569626,
|
| 718 |
+
"learning_rate": 4.932444364939205e-05,
|
| 719 |
+
"loss": 0.292,
|
| 720 |
+
"num_input_tokens_seen": 6482728,
|
| 721 |
+
"step": 89
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.4818276220145379,
|
| 725 |
+
"grad_norm": 0.08270515501499176,
|
| 726 |
+
"learning_rate": 4.9309248009941914e-05,
|
| 727 |
+
"loss": 0.3472,
|
| 728 |
+
"num_input_tokens_seen": 6562104,
|
| 729 |
+
"step": 90
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.4984423676012462,
|
| 733 |
+
"grad_norm": 0.07407747954130173,
|
| 734 |
+
"learning_rate": 4.929388575762782e-05,
|
| 735 |
+
"loss": 0.2995,
|
| 736 |
+
"num_input_tokens_seen": 6656552,
|
| 737 |
+
"step": 91
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.5150571131879542,
|
| 741 |
+
"grad_norm": 0.08710360527038574,
|
| 742 |
+
"learning_rate": 4.9278356997740904e-05,
|
| 743 |
+
"loss": 0.2549,
|
| 744 |
+
"num_input_tokens_seen": 6714184,
|
| 745 |
+
"step": 92
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.5316718587746625,
|
| 749 |
+
"grad_norm": 0.0773790255188942,
|
| 750 |
+
"learning_rate": 4.9262661836713564e-05,
|
| 751 |
+
"loss": 0.2814,
|
| 752 |
+
"num_input_tokens_seen": 6793552,
|
| 753 |
+
"step": 93
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.5482866043613708,
|
| 757 |
+
"grad_norm": 0.1002134457230568,
|
| 758 |
+
"learning_rate": 4.924680038211867e-05,
|
| 759 |
+
"loss": 0.2876,
|
| 760 |
+
"num_input_tokens_seen": 6865256,
|
| 761 |
+
"step": 94
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.5649013499480788,
|
| 765 |
+
"grad_norm": 0.09670394659042358,
|
| 766 |
+
"learning_rate": 4.9230772742668866e-05,
|
| 767 |
+
"loss": 0.2846,
|
| 768 |
+
"num_input_tokens_seen": 6931152,
|
| 769 |
+
"step": 95
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.5815160955347871,
|
| 773 |
+
"grad_norm": 0.08910100907087326,
|
| 774 |
+
"learning_rate": 4.9214579028215776e-05,
|
| 775 |
+
"loss": 0.2944,
|
| 776 |
+
"num_input_tokens_seen": 6998408,
|
| 777 |
+
"step": 96
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.5981308411214954,
|
| 781 |
+
"grad_norm": 0.09202459454536438,
|
| 782 |
+
"learning_rate": 4.919821934974933e-05,
|
| 783 |
+
"loss": 0.251,
|
| 784 |
+
"num_input_tokens_seen": 7053008,
|
| 785 |
+
"step": 97
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.6147455867082035,
|
| 789 |
+
"grad_norm": 0.10218881815671921,
|
| 790 |
+
"learning_rate": 4.918169381939692e-05,
|
| 791 |
+
"loss": 0.2851,
|
| 792 |
+
"num_input_tokens_seen": 7106440,
|
| 793 |
+
"step": 98
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.6313603322949117,
|
| 797 |
+
"grad_norm": 0.09290914982557297,
|
| 798 |
+
"learning_rate": 4.916500255042268e-05,
|
| 799 |
+
"loss": 0.2959,
|
| 800 |
+
"num_input_tokens_seen": 7167032,
|
| 801 |
+
"step": 99
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.64797507788162,
|
| 805 |
+
"grad_norm": 0.07791033387184143,
|
| 806 |
+
"learning_rate": 4.914814565722671e-05,
|
| 807 |
+
"loss": 0.2481,
|
| 808 |
+
"num_input_tokens_seen": 7245720,
|
| 809 |
+
"step": 100
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.664589823468328,
|
| 813 |
+
"grad_norm": 0.08885534107685089,
|
| 814 |
+
"learning_rate": 4.913112325534426e-05,
|
| 815 |
+
"loss": 0.3168,
|
| 816 |
+
"num_input_tokens_seen": 7326320,
|
| 817 |
+
"step": 101
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 1.6812045690550363,
|
| 821 |
+
"grad_norm": 0.08569750934839249,
|
| 822 |
+
"learning_rate": 4.9113935461444955e-05,
|
| 823 |
+
"loss": 0.2805,
|
| 824 |
+
"num_input_tokens_seen": 7442232,
|
| 825 |
+
"step": 102
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.6978193146417446,
|
| 829 |
+
"grad_norm": 0.1112508773803711,
|
| 830 |
+
"learning_rate": 4.9096582393332025e-05,
|
| 831 |
+
"loss": 0.2675,
|
| 832 |
+
"num_input_tokens_seen": 7502496,
|
| 833 |
+
"step": 103
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.7144340602284527,
|
| 837 |
+
"grad_norm": 0.09654372185468674,
|
| 838 |
+
"learning_rate": 4.907906416994146e-05,
|
| 839 |
+
"loss": 0.3038,
|
| 840 |
+
"num_input_tokens_seen": 7566496,
|
| 841 |
+
"step": 104
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.731048805815161,
|
| 845 |
+
"grad_norm": 0.10022995620965958,
|
| 846 |
+
"learning_rate": 4.906138091134118e-05,
|
| 847 |
+
"loss": 0.3639,
|
| 848 |
+
"num_input_tokens_seen": 7629056,
|
| 849 |
+
"step": 105
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.7476635514018692,
|
| 853 |
+
"grad_norm": 0.08336564153432846,
|
| 854 |
+
"learning_rate": 4.9043532738730284e-05,
|
| 855 |
+
"loss": 0.2944,
|
| 856 |
+
"num_input_tokens_seen": 7706096,
|
| 857 |
+
"step": 106
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.7642782969885773,
|
| 861 |
+
"grad_norm": 0.08539658784866333,
|
| 862 |
+
"learning_rate": 4.9025519774438136e-05,
|
| 863 |
+
"loss": 0.2392,
|
| 864 |
+
"num_input_tokens_seen": 7780072,
|
| 865 |
+
"step": 107
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.7808930425752856,
|
| 869 |
+
"grad_norm": 0.09139693528413773,
|
| 870 |
+
"learning_rate": 4.900734214192358e-05,
|
| 871 |
+
"loss": 0.2685,
|
| 872 |
+
"num_input_tokens_seen": 7857712,
|
| 873 |
+
"step": 108
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.7975077881619939,
|
| 877 |
+
"grad_norm": 0.1043916717171669,
|
| 878 |
+
"learning_rate": 4.898899996577407e-05,
|
| 879 |
+
"loss": 0.2513,
|
| 880 |
+
"num_input_tokens_seen": 7916832,
|
| 881 |
+
"step": 109
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 1.814122533748702,
|
| 885 |
+
"grad_norm": 0.09203662723302841,
|
| 886 |
+
"learning_rate": 4.8970493371704826e-05,
|
| 887 |
+
"loss": 0.2974,
|
| 888 |
+
"num_input_tokens_seen": 7993056,
|
| 889 |
+
"step": 110
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.8307372793354102,
|
| 893 |
+
"grad_norm": 0.09319474548101425,
|
| 894 |
+
"learning_rate": 4.8951822486557986e-05,
|
| 895 |
+
"loss": 0.3096,
|
| 896 |
+
"num_input_tokens_seen": 8090056,
|
| 897 |
+
"step": 111
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.8473520249221185,
|
| 901 |
+
"grad_norm": 0.10193445533514023,
|
| 902 |
+
"learning_rate": 4.893298743830168e-05,
|
| 903 |
+
"loss": 0.2633,
|
| 904 |
+
"num_input_tokens_seen": 8164808,
|
| 905 |
+
"step": 112
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.8639667705088265,
|
| 909 |
+
"grad_norm": 0.11407948285341263,
|
| 910 |
+
"learning_rate": 4.891398835602925e-05,
|
| 911 |
+
"loss": 0.2584,
|
| 912 |
+
"num_input_tokens_seen": 8223568,
|
| 913 |
+
"step": 113
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.8805815160955348,
|
| 917 |
+
"grad_norm": 0.11977085471153259,
|
| 918 |
+
"learning_rate": 4.8894825369958255e-05,
|
| 919 |
+
"loss": 0.2619,
|
| 920 |
+
"num_input_tokens_seen": 8276160,
|
| 921 |
+
"step": 114
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.897196261682243,
|
| 925 |
+
"grad_norm": 0.10925433784723282,
|
| 926 |
+
"learning_rate": 4.8875498611429674e-05,
|
| 927 |
+
"loss": 0.2762,
|
| 928 |
+
"num_input_tokens_seen": 8354904,
|
| 929 |
+
"step": 115
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.9138110072689511,
|
| 933 |
+
"grad_norm": 0.09673939645290375,
|
| 934 |
+
"learning_rate": 4.8856008212906925e-05,
|
| 935 |
+
"loss": 0.3152,
|
| 936 |
+
"num_input_tokens_seen": 8442584,
|
| 937 |
+
"step": 116
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 1.9304257528556594,
|
| 941 |
+
"grad_norm": 0.10827789455652237,
|
| 942 |
+
"learning_rate": 4.8836354307975026e-05,
|
| 943 |
+
"loss": 0.2759,
|
| 944 |
+
"num_input_tokens_seen": 8506688,
|
| 945 |
+
"step": 117
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.9470404984423677,
|
| 949 |
+
"grad_norm": 0.08390220254659653,
|
| 950 |
+
"learning_rate": 4.881653703133966e-05,
|
| 951 |
+
"loss": 0.2192,
|
| 952 |
+
"num_input_tokens_seen": 8610712,
|
| 953 |
+
"step": 118
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.9636552440290758,
|
| 957 |
+
"grad_norm": 0.09252211451530457,
|
| 958 |
+
"learning_rate": 4.87965565188262e-05,
|
| 959 |
+
"loss": 0.2618,
|
| 960 |
+
"num_input_tokens_seen": 8692624,
|
| 961 |
+
"step": 119
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.980269989615784,
|
| 965 |
+
"grad_norm": 0.1107102632522583,
|
| 966 |
+
"learning_rate": 4.877641290737884e-05,
|
| 967 |
+
"loss": 0.2666,
|
| 968 |
+
"num_input_tokens_seen": 8772208,
|
| 969 |
+
"step": 120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.9968847352024923,
|
| 973 |
+
"grad_norm": 0.0917077362537384,
|
| 974 |
+
"learning_rate": 4.8756106335059646e-05,
|
| 975 |
+
"loss": 0.253,
|
| 976 |
+
"num_input_tokens_seen": 8854904,
|
| 977 |
+
"step": 121
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.0,
|
| 981 |
+
"grad_norm": 0.2606711685657501,
|
| 982 |
+
"learning_rate": 4.87356369410476e-05,
|
| 983 |
+
"loss": 0.235,
|
| 984 |
+
"num_input_tokens_seen": 8872656,
|
| 985 |
+
"step": 122
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.016614745586708,
|
| 989 |
+
"grad_norm": 0.10363993793725967,
|
| 990 |
+
"learning_rate": 4.8715004865637614e-05,
|
| 991 |
+
"loss": 0.266,
|
| 992 |
+
"num_input_tokens_seen": 8946480,
|
| 993 |
+
"step": 123
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.0332294911734166,
|
| 997 |
+
"grad_norm": 0.09997844696044922,
|
| 998 |
+
"learning_rate": 4.869421025023965e-05,
|
| 999 |
+
"loss": 0.2696,
|
| 1000 |
+
"num_input_tokens_seen": 9023328,
|
| 1001 |
+
"step": 124
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 2.0498442367601246,
|
| 1005 |
+
"grad_norm": 0.13349319994449615,
|
| 1006 |
+
"learning_rate": 4.867325323737765e-05,
|
| 1007 |
+
"loss": 0.2552,
|
| 1008 |
+
"num_input_tokens_seen": 9074320,
|
| 1009 |
+
"step": 125
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 2.0664589823468327,
|
| 1013 |
+
"grad_norm": 0.11201464384794235,
|
| 1014 |
+
"learning_rate": 4.8652133970688636e-05,
|
| 1015 |
+
"loss": 0.2486,
|
| 1016 |
+
"num_input_tokens_seen": 9148784,
|
| 1017 |
+
"step": 126
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.083073727933541,
|
| 1021 |
+
"grad_norm": 0.10193142294883728,
|
| 1022 |
+
"learning_rate": 4.8630852594921706e-05,
|
| 1023 |
+
"loss": 0.2814,
|
| 1024 |
+
"num_input_tokens_seen": 9246624,
|
| 1025 |
+
"step": 127
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.0996884735202492,
|
| 1029 |
+
"grad_norm": 0.1305130422115326,
|
| 1030 |
+
"learning_rate": 4.860940925593703e-05,
|
| 1031 |
+
"loss": 0.304,
|
| 1032 |
+
"num_input_tokens_seen": 9328176,
|
| 1033 |
+
"step": 128
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.1163032191069573,
|
| 1037 |
+
"grad_norm": 0.1137692779302597,
|
| 1038 |
+
"learning_rate": 4.8587804100704845e-05,
|
| 1039 |
+
"loss": 0.2427,
|
| 1040 |
+
"num_input_tokens_seen": 9388936,
|
| 1041 |
+
"step": 129
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.132917964693666,
|
| 1045 |
+
"grad_norm": 0.12126237154006958,
|
| 1046 |
+
"learning_rate": 4.856603727730447e-05,
|
| 1047 |
+
"loss": 0.2485,
|
| 1048 |
+
"num_input_tokens_seen": 9461664,
|
| 1049 |
+
"step": 130
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.149532710280374,
|
| 1053 |
+
"grad_norm": 0.11567176878452301,
|
| 1054 |
+
"learning_rate": 4.854410893492326e-05,
|
| 1055 |
+
"loss": 0.2628,
|
| 1056 |
+
"num_input_tokens_seen": 9535000,
|
| 1057 |
+
"step": 131
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 2.166147455867082,
|
| 1061 |
+
"grad_norm": 0.1399552971124649,
|
| 1062 |
+
"learning_rate": 4.852201922385564e-05,
|
| 1063 |
+
"loss": 0.2518,
|
| 1064 |
+
"num_input_tokens_seen": 9600296,
|
| 1065 |
+
"step": 132
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.1827622014537904,
|
| 1069 |
+
"grad_norm": 0.13912151753902435,
|
| 1070 |
+
"learning_rate": 4.8499768295502004e-05,
|
| 1071 |
+
"loss": 0.2429,
|
| 1072 |
+
"num_input_tokens_seen": 9686784,
|
| 1073 |
+
"step": 133
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.1993769470404985,
|
| 1077 |
+
"grad_norm": 0.11130474507808685,
|
| 1078 |
+
"learning_rate": 4.847735630236773e-05,
|
| 1079 |
+
"loss": 0.2775,
|
| 1080 |
+
"num_input_tokens_seen": 9781112,
|
| 1081 |
+
"step": 134
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.2159916926272065,
|
| 1085 |
+
"grad_norm": 0.12169156968593597,
|
| 1086 |
+
"learning_rate": 4.8454783398062106e-05,
|
| 1087 |
+
"loss": 0.2439,
|
| 1088 |
+
"num_input_tokens_seen": 9849528,
|
| 1089 |
+
"step": 135
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.232606438213915,
|
| 1093 |
+
"grad_norm": 0.11766713112592697,
|
| 1094 |
+
"learning_rate": 4.843204973729729e-05,
|
| 1095 |
+
"loss": 0.2538,
|
| 1096 |
+
"num_input_tokens_seen": 9931080,
|
| 1097 |
+
"step": 136
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.249221183800623,
|
| 1101 |
+
"grad_norm": 0.11854218691587448,
|
| 1102 |
+
"learning_rate": 4.840915547588725e-05,
|
| 1103 |
+
"loss": 0.2782,
|
| 1104 |
+
"num_input_tokens_seen": 10011176,
|
| 1105 |
+
"step": 137
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 2.265835929387331,
|
| 1109 |
+
"grad_norm": 0.1340581178665161,
|
| 1110 |
+
"learning_rate": 4.838610077074669e-05,
|
| 1111 |
+
"loss": 0.248,
|
| 1112 |
+
"num_input_tokens_seen": 10084128,
|
| 1113 |
+
"step": 138
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.2824506749740396,
|
| 1117 |
+
"grad_norm": 0.12075436115264893,
|
| 1118 |
+
"learning_rate": 4.836288577988996e-05,
|
| 1119 |
+
"loss": 0.2582,
|
| 1120 |
+
"num_input_tokens_seen": 10155536,
|
| 1121 |
+
"step": 139
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 2.2990654205607477,
|
| 1125 |
+
"grad_norm": 0.10599923878908157,
|
| 1126 |
+
"learning_rate": 4.8339510662430046e-05,
|
| 1127 |
+
"loss": 0.2199,
|
| 1128 |
+
"num_input_tokens_seen": 10251160,
|
| 1129 |
+
"step": 140
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.3156801661474558,
|
| 1133 |
+
"grad_norm": 0.1117846742272377,
|
| 1134 |
+
"learning_rate": 4.8315975578577355e-05,
|
| 1135 |
+
"loss": 0.2324,
|
| 1136 |
+
"num_input_tokens_seen": 10345864,
|
| 1137 |
+
"step": 141
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.3322949117341643,
|
| 1141 |
+
"grad_norm": 0.13972057402133942,
|
| 1142 |
+
"learning_rate": 4.8292280689638725e-05,
|
| 1143 |
+
"loss": 0.4072,
|
| 1144 |
+
"num_input_tokens_seen": 10417616,
|
| 1145 |
+
"step": 142
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.3489096573208723,
|
| 1149 |
+
"grad_norm": 0.13837860524654388,
|
| 1150 |
+
"learning_rate": 4.826842615801628e-05,
|
| 1151 |
+
"loss": 0.2607,
|
| 1152 |
+
"num_input_tokens_seen": 10481816,
|
| 1153 |
+
"step": 143
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.3655244029075804,
|
| 1157 |
+
"grad_norm": 0.14040137827396393,
|
| 1158 |
+
"learning_rate": 4.8244412147206284e-05,
|
| 1159 |
+
"loss": 0.3094,
|
| 1160 |
+
"num_input_tokens_seen": 10562056,
|
| 1161 |
+
"step": 144
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.382139148494289,
|
| 1165 |
+
"grad_norm": 0.1393299251794815,
|
| 1166 |
+
"learning_rate": 4.822023882179811e-05,
|
| 1167 |
+
"loss": 0.2407,
|
| 1168 |
+
"num_input_tokens_seen": 10612808,
|
| 1169 |
+
"step": 145
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 2.398753894080997,
|
| 1173 |
+
"grad_norm": 0.13878698647022247,
|
| 1174 |
+
"learning_rate": 4.8195906347473e-05,
|
| 1175 |
+
"loss": 0.2481,
|
| 1176 |
+
"num_input_tokens_seen": 10682328,
|
| 1177 |
+
"step": 146
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.415368639667705,
|
| 1181 |
+
"grad_norm": 0.10430227965116501,
|
| 1182 |
+
"learning_rate": 4.817141489100302e-05,
|
| 1183 |
+
"loss": 0.2528,
|
| 1184 |
+
"num_input_tokens_seen": 10771912,
|
| 1185 |
+
"step": 147
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.431983385254413,
|
| 1189 |
+
"grad_norm": 0.12963703274726868,
|
| 1190 |
+
"learning_rate": 4.814676462024988e-05,
|
| 1191 |
+
"loss": 0.2739,
|
| 1192 |
+
"num_input_tokens_seen": 10842232,
|
| 1193 |
+
"step": 148
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.4485981308411215,
|
| 1197 |
+
"grad_norm": 0.13274963200092316,
|
| 1198 |
+
"learning_rate": 4.8121955704163745e-05,
|
| 1199 |
+
"loss": 0.2407,
|
| 1200 |
+
"num_input_tokens_seen": 10902264,
|
| 1201 |
+
"step": 149
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.4652128764278296,
|
| 1205 |
+
"grad_norm": 0.11079717427492142,
|
| 1206 |
+
"learning_rate": 4.8096988312782174e-05,
|
| 1207 |
+
"loss": 0.2142,
|
| 1208 |
+
"num_input_tokens_seen": 10992744,
|
| 1209 |
+
"step": 150
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.4818276220145377,
|
| 1213 |
+
"grad_norm": 0.08429212868213654,
|
| 1214 |
+
"learning_rate": 4.8071862617228855e-05,
|
| 1215 |
+
"loss": 0.1428,
|
| 1216 |
+
"num_input_tokens_seen": 11090064,
|
| 1217 |
+
"step": 151
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 2.498442367601246,
|
| 1221 |
+
"grad_norm": 0.12903761863708496,
|
| 1222 |
+
"learning_rate": 4.8046578789712515e-05,
|
| 1223 |
+
"loss": 0.2268,
|
| 1224 |
+
"num_input_tokens_seen": 11162864,
|
| 1225 |
+
"step": 152
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 2.515057113187954,
|
| 1229 |
+
"grad_norm": 0.14638672769069672,
|
| 1230 |
+
"learning_rate": 4.8021137003525664e-05,
|
| 1231 |
+
"loss": 0.2388,
|
| 1232 |
+
"num_input_tokens_seen": 11224368,
|
| 1233 |
+
"step": 153
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.5316718587746623,
|
| 1237 |
+
"grad_norm": 0.1372838169336319,
|
| 1238 |
+
"learning_rate": 4.7995537433043446e-05,
|
| 1239 |
+
"loss": 0.2588,
|
| 1240 |
+
"num_input_tokens_seen": 11291056,
|
| 1241 |
+
"step": 154
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.5482866043613708,
|
| 1245 |
+
"grad_norm": 0.15665481984615326,
|
| 1246 |
+
"learning_rate": 4.796978025372246e-05,
|
| 1247 |
+
"loss": 0.2225,
|
| 1248 |
+
"num_input_tokens_seen": 11345464,
|
| 1249 |
+
"step": 155
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.564901349948079,
|
| 1253 |
+
"grad_norm": 0.13234855234622955,
|
| 1254 |
+
"learning_rate": 4.794386564209953e-05,
|
| 1255 |
+
"loss": 0.275,
|
| 1256 |
+
"num_input_tokens_seen": 11418912,
|
| 1257 |
+
"step": 156
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.581516095534787,
|
| 1261 |
+
"grad_norm": 0.13585953414440155,
|
| 1262 |
+
"learning_rate": 4.79177937757905e-05,
|
| 1263 |
+
"loss": 0.2407,
|
| 1264 |
+
"num_input_tokens_seen": 11491216,
|
| 1265 |
+
"step": 157
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 2.5981308411214954,
|
| 1269 |
+
"grad_norm": 0.1423913538455963,
|
| 1270 |
+
"learning_rate": 4.7891564833489035e-05,
|
| 1271 |
+
"loss": 0.1971,
|
| 1272 |
+
"num_input_tokens_seen": 11558016,
|
| 1273 |
+
"step": 158
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.6147455867082035,
|
| 1277 |
+
"grad_norm": 0.13013511896133423,
|
| 1278 |
+
"learning_rate": 4.7865178994965344e-05,
|
| 1279 |
+
"loss": 0.2362,
|
| 1280 |
+
"num_input_tokens_seen": 11630432,
|
| 1281 |
+
"step": 159
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.6313603322949115,
|
| 1285 |
+
"grad_norm": 0.1587141752243042,
|
| 1286 |
+
"learning_rate": 4.783863644106502e-05,
|
| 1287 |
+
"loss": 0.2252,
|
| 1288 |
+
"num_input_tokens_seen": 11684624,
|
| 1289 |
+
"step": 160
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 2.64797507788162,
|
| 1293 |
+
"grad_norm": 0.12592960894107819,
|
| 1294 |
+
"learning_rate": 4.781193735370777e-05,
|
| 1295 |
+
"loss": 0.2506,
|
| 1296 |
+
"num_input_tokens_seen": 11770232,
|
| 1297 |
+
"step": 161
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.664589823468328,
|
| 1301 |
+
"grad_norm": 0.1583249419927597,
|
| 1302 |
+
"learning_rate": 4.7785081915886134e-05,
|
| 1303 |
+
"loss": 0.2352,
|
| 1304 |
+
"num_input_tokens_seen": 11828360,
|
| 1305 |
+
"step": 162
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.681204569055036,
|
| 1309 |
+
"grad_norm": 0.14881783723831177,
|
| 1310 |
+
"learning_rate": 4.775807031166428e-05,
|
| 1311 |
+
"loss": 0.2308,
|
| 1312 |
+
"num_input_tokens_seen": 11915944,
|
| 1313 |
+
"step": 163
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.6978193146417446,
|
| 1317 |
+
"grad_norm": 0.1607823222875595,
|
| 1318 |
+
"learning_rate": 4.773090272617672e-05,
|
| 1319 |
+
"loss": 0.2238,
|
| 1320 |
+
"num_input_tokens_seen": 11981792,
|
| 1321 |
+
"step": 164
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 2.7144340602284527,
|
| 1325 |
+
"grad_norm": 0.13583113253116608,
|
| 1326 |
+
"learning_rate": 4.7703579345627035e-05,
|
| 1327 |
+
"loss": 0.3196,
|
| 1328 |
+
"num_input_tokens_seen": 12044024,
|
| 1329 |
+
"step": 165
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.7310488058151607,
|
| 1333 |
+
"grad_norm": 0.19167298078536987,
|
| 1334 |
+
"learning_rate": 4.7676100357286624e-05,
|
| 1335 |
+
"loss": 0.2745,
|
| 1336 |
+
"num_input_tokens_seen": 12093424,
|
| 1337 |
+
"step": 166
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 2.7476635514018692,
|
| 1341 |
+
"grad_norm": 0.130703404545784,
|
| 1342 |
+
"learning_rate": 4.76484659494934e-05,
|
| 1343 |
+
"loss": 0.2285,
|
| 1344 |
+
"num_input_tokens_seen": 12167792,
|
| 1345 |
+
"step": 167
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 2.7642782969885773,
|
| 1349 |
+
"grad_norm": 0.14331185817718506,
|
| 1350 |
+
"learning_rate": 4.762067631165049e-05,
|
| 1351 |
+
"loss": 0.2506,
|
| 1352 |
+
"num_input_tokens_seen": 12233712,
|
| 1353 |
+
"step": 168
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.7808930425752854,
|
| 1357 |
+
"grad_norm": 0.12700341641902924,
|
| 1358 |
+
"learning_rate": 4.7592731634224966e-05,
|
| 1359 |
+
"loss": 0.2052,
|
| 1360 |
+
"num_input_tokens_seen": 12310544,
|
| 1361 |
+
"step": 169
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.797507788161994,
|
| 1365 |
+
"grad_norm": 0.15118420124053955,
|
| 1366 |
+
"learning_rate": 4.756463210874652e-05,
|
| 1367 |
+
"loss": 0.2309,
|
| 1368 |
+
"num_input_tokens_seen": 12400160,
|
| 1369 |
+
"step": 170
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.814122533748702,
|
| 1373 |
+
"grad_norm": 0.14001020789146423,
|
| 1374 |
+
"learning_rate": 4.753637792780614e-05,
|
| 1375 |
+
"loss": 0.2544,
|
| 1376 |
+
"num_input_tokens_seen": 12480432,
|
| 1377 |
+
"step": 171
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.83073727933541,
|
| 1381 |
+
"grad_norm": 0.12076311558485031,
|
| 1382 |
+
"learning_rate": 4.7507969285054845e-05,
|
| 1383 |
+
"loss": 0.2434,
|
| 1384 |
+
"num_input_tokens_seen": 12568064,
|
| 1385 |
+
"step": 172
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.8473520249221185,
|
| 1389 |
+
"grad_norm": 0.16462342441082,
|
| 1390 |
+
"learning_rate": 4.7479406375202264e-05,
|
| 1391 |
+
"loss": 0.2417,
|
| 1392 |
+
"num_input_tokens_seen": 12647400,
|
| 1393 |
+
"step": 173
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 2.8639667705088265,
|
| 1397 |
+
"grad_norm": 0.17294971644878387,
|
| 1398 |
+
"learning_rate": 4.745068939401539e-05,
|
| 1399 |
+
"loss": 0.2121,
|
| 1400 |
+
"num_input_tokens_seen": 12698208,
|
| 1401 |
+
"step": 174
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 2.8805815160955346,
|
| 1405 |
+
"grad_norm": 0.16743803024291992,
|
| 1406 |
+
"learning_rate": 4.742181853831721e-05,
|
| 1407 |
+
"loss": 0.2238,
|
| 1408 |
+
"num_input_tokens_seen": 12758528,
|
| 1409 |
+
"step": 175
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 2.897196261682243,
|
| 1413 |
+
"grad_norm": 0.14583320915699005,
|
| 1414 |
+
"learning_rate": 4.7392794005985326e-05,
|
| 1415 |
+
"loss": 0.2333,
|
| 1416 |
+
"num_input_tokens_seen": 12837264,
|
| 1417 |
+
"step": 176
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.913811007268951,
|
| 1421 |
+
"grad_norm": 0.1509270817041397,
|
| 1422 |
+
"learning_rate": 4.7363615995950626e-05,
|
| 1423 |
+
"loss": 0.2179,
|
| 1424 |
+
"num_input_tokens_seen": 12902368,
|
| 1425 |
+
"step": 177
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.930425752855659,
|
| 1429 |
+
"grad_norm": 0.12910738587379456,
|
| 1430 |
+
"learning_rate": 4.733428470819594e-05,
|
| 1431 |
+
"loss": 0.2144,
|
| 1432 |
+
"num_input_tokens_seen": 12974296,
|
| 1433 |
+
"step": 178
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 2.9470404984423677,
|
| 1437 |
+
"grad_norm": 0.142000213265419,
|
| 1438 |
+
"learning_rate": 4.730480034375462e-05,
|
| 1439 |
+
"loss": 0.2413,
|
| 1440 |
+
"num_input_tokens_seen": 13057280,
|
| 1441 |
+
"step": 179
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.9636552440290758,
|
| 1445 |
+
"grad_norm": 0.131468266248703,
|
| 1446 |
+
"learning_rate": 4.72751631047092e-05,
|
| 1447 |
+
"loss": 0.294,
|
| 1448 |
+
"num_input_tokens_seen": 13158232,
|
| 1449 |
+
"step": 180
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.980269989615784,
|
| 1453 |
+
"grad_norm": 0.1529342085123062,
|
| 1454 |
+
"learning_rate": 4.7245373194189994e-05,
|
| 1455 |
+
"loss": 0.216,
|
| 1456 |
+
"num_input_tokens_seen": 13229840,
|
| 1457 |
+
"step": 181
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 2.9968847352024923,
|
| 1461 |
+
"grad_norm": 0.1573815941810608,
|
| 1462 |
+
"learning_rate": 4.7215430816373726e-05,
|
| 1463 |
+
"loss": 0.2384,
|
| 1464 |
+
"num_input_tokens_seen": 13296520,
|
| 1465 |
+
"step": 182
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 3.0,
|
| 1469 |
+
"grad_norm": 0.2532118558883667,
|
| 1470 |
+
"learning_rate": 4.718533617648209e-05,
|
| 1471 |
+
"loss": 0.1459,
|
| 1472 |
+
"num_input_tokens_seen": 13309672,
|
| 1473 |
+
"step": 183
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.016614745586708,
|
| 1477 |
+
"grad_norm": 0.16963432729244232,
|
| 1478 |
+
"learning_rate": 4.715508948078037e-05,
|
| 1479 |
+
"loss": 0.1985,
|
| 1480 |
+
"num_input_tokens_seen": 13371544,
|
| 1481 |
+
"step": 184
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 3.0332294911734166,
|
| 1485 |
+
"grad_norm": 0.18877384066581726,
|
| 1486 |
+
"learning_rate": 4.712469093657605e-05,
|
| 1487 |
+
"loss": 0.1856,
|
| 1488 |
+
"num_input_tokens_seen": 13432984,
|
| 1489 |
+
"step": 185
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 3.0498442367601246,
|
| 1493 |
+
"grad_norm": 0.14922884106636047,
|
| 1494 |
+
"learning_rate": 4.709414075221734e-05,
|
| 1495 |
+
"loss": 0.2385,
|
| 1496 |
+
"num_input_tokens_seen": 13500016,
|
| 1497 |
+
"step": 186
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 3.0664589823468327,
|
| 1501 |
+
"grad_norm": 0.2028326541185379,
|
| 1502 |
+
"learning_rate": 4.706343913709178e-05,
|
| 1503 |
+
"loss": 0.2227,
|
| 1504 |
+
"num_input_tokens_seen": 13579672,
|
| 1505 |
+
"step": 187
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.083073727933541,
|
| 1509 |
+
"grad_norm": 0.19964616000652313,
|
| 1510 |
+
"learning_rate": 4.70325863016248e-05,
|
| 1511 |
+
"loss": 0.2045,
|
| 1512 |
+
"num_input_tokens_seen": 13630704,
|
| 1513 |
+
"step": 188
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 3.0996884735202492,
|
| 1517 |
+
"grad_norm": 0.1594657599925995,
|
| 1518 |
+
"learning_rate": 4.7001582457278304e-05,
|
| 1519 |
+
"loss": 0.2648,
|
| 1520 |
+
"num_input_tokens_seen": 13695472,
|
| 1521 |
+
"step": 189
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 3.1163032191069573,
|
| 1525 |
+
"grad_norm": 0.16952532529830933,
|
| 1526 |
+
"learning_rate": 4.697042781654913e-05,
|
| 1527 |
+
"loss": 0.22,
|
| 1528 |
+
"num_input_tokens_seen": 13767792,
|
| 1529 |
+
"step": 190
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 3.132917964693666,
|
| 1533 |
+
"grad_norm": 0.16775831580162048,
|
| 1534 |
+
"learning_rate": 4.693912259296773e-05,
|
| 1535 |
+
"loss": 0.2667,
|
| 1536 |
+
"num_input_tokens_seen": 13857352,
|
| 1537 |
+
"step": 191
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 3.149532710280374,
|
| 1541 |
+
"grad_norm": 0.15529580414295197,
|
| 1542 |
+
"learning_rate": 4.690766700109659e-05,
|
| 1543 |
+
"loss": 0.2154,
|
| 1544 |
+
"num_input_tokens_seen": 13939928,
|
| 1545 |
+
"step": 192
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 3.166147455867082,
|
| 1549 |
+
"grad_norm": 0.1619848757982254,
|
| 1550 |
+
"learning_rate": 4.687606125652882e-05,
|
| 1551 |
+
"loss": 0.1963,
|
| 1552 |
+
"num_input_tokens_seen": 14017936,
|
| 1553 |
+
"step": 193
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 3.1827622014537904,
|
| 1557 |
+
"grad_norm": 0.18066684901714325,
|
| 1558 |
+
"learning_rate": 4.684430557588664e-05,
|
| 1559 |
+
"loss": 0.1862,
|
| 1560 |
+
"num_input_tokens_seen": 14074176,
|
| 1561 |
+
"step": 194
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 3.1993769470404985,
|
| 1565 |
+
"grad_norm": 0.16520777344703674,
|
| 1566 |
+
"learning_rate": 4.681240017681993e-05,
|
| 1567 |
+
"loss": 0.2576,
|
| 1568 |
+
"num_input_tokens_seen": 14167656,
|
| 1569 |
+
"step": 195
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 3.2159916926272065,
|
| 1573 |
+
"grad_norm": 0.15385325253009796,
|
| 1574 |
+
"learning_rate": 4.678034527800474e-05,
|
| 1575 |
+
"loss": 0.1813,
|
| 1576 |
+
"num_input_tokens_seen": 14235800,
|
| 1577 |
+
"step": 196
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 3.232606438213915,
|
| 1581 |
+
"grad_norm": 0.16897696256637573,
|
| 1582 |
+
"learning_rate": 4.674814109914174e-05,
|
| 1583 |
+
"loss": 0.1741,
|
| 1584 |
+
"num_input_tokens_seen": 14301272,
|
| 1585 |
+
"step": 197
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.249221183800623,
|
| 1589 |
+
"grad_norm": 0.19556447863578796,
|
| 1590 |
+
"learning_rate": 4.671578786095478e-05,
|
| 1591 |
+
"loss": 0.2186,
|
| 1592 |
+
"num_input_tokens_seen": 14347352,
|
| 1593 |
+
"step": 198
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 3.265835929387331,
|
| 1597 |
+
"grad_norm": 0.17333142459392548,
|
| 1598 |
+
"learning_rate": 4.668328578518933e-05,
|
| 1599 |
+
"loss": 0.2892,
|
| 1600 |
+
"num_input_tokens_seen": 14434600,
|
| 1601 |
+
"step": 199
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 3.2824506749740396,
|
| 1605 |
+
"grad_norm": 0.20295488834381104,
|
| 1606 |
+
"learning_rate": 4.665063509461097e-05,
|
| 1607 |
+
"loss": 0.2014,
|
| 1608 |
+
"num_input_tokens_seen": 14484104,
|
| 1609 |
+
"step": 200
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 3.2990654205607477,
|
| 1613 |
+
"grad_norm": 0.1597638726234436,
|
| 1614 |
+
"learning_rate": 4.661783601300388e-05,
|
| 1615 |
+
"loss": 0.2158,
|
| 1616 |
+
"num_input_tokens_seen": 14567152,
|
| 1617 |
+
"step": 201
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 3.3156801661474558,
|
| 1621 |
+
"grad_norm": 0.19849488139152527,
|
| 1622 |
+
"learning_rate": 4.6584888765169296e-05,
|
| 1623 |
+
"loss": 0.2578,
|
| 1624 |
+
"num_input_tokens_seen": 14647040,
|
| 1625 |
+
"step": 202
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 3.3322949117341643,
|
| 1629 |
+
"grad_norm": 0.1508200466632843,
|
| 1630 |
+
"learning_rate": 4.6551793576923964e-05,
|
| 1631 |
+
"loss": 0.2213,
|
| 1632 |
+
"num_input_tokens_seen": 14738216,
|
| 1633 |
+
"step": 203
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 3.3489096573208723,
|
| 1637 |
+
"grad_norm": 0.1687687337398529,
|
| 1638 |
+
"learning_rate": 4.65185506750986e-05,
|
| 1639 |
+
"loss": 0.1828,
|
| 1640 |
+
"num_input_tokens_seen": 14811216,
|
| 1641 |
+
"step": 204
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.3655244029075804,
|
| 1645 |
+
"grad_norm": 0.16587376594543457,
|
| 1646 |
+
"learning_rate": 4.648516028753632e-05,
|
| 1647 |
+
"loss": 0.1619,
|
| 1648 |
+
"num_input_tokens_seen": 14885992,
|
| 1649 |
+
"step": 205
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 3.382139148494289,
|
| 1653 |
+
"grad_norm": 0.16600169241428375,
|
| 1654 |
+
"learning_rate": 4.645162264309112e-05,
|
| 1655 |
+
"loss": 0.2438,
|
| 1656 |
+
"num_input_tokens_seen": 14961984,
|
| 1657 |
+
"step": 206
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 3.398753894080997,
|
| 1661 |
+
"grad_norm": 0.1877703070640564,
|
| 1662 |
+
"learning_rate": 4.6417937971626245e-05,
|
| 1663 |
+
"loss": 0.1771,
|
| 1664 |
+
"num_input_tokens_seen": 15021240,
|
| 1665 |
+
"step": 207
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 3.415368639667705,
|
| 1669 |
+
"grad_norm": 0.20105206966400146,
|
| 1670 |
+
"learning_rate": 4.638410650401267e-05,
|
| 1671 |
+
"loss": 0.1742,
|
| 1672 |
+
"num_input_tokens_seen": 15092016,
|
| 1673 |
+
"step": 208
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 3.431983385254413,
|
| 1677 |
+
"grad_norm": 0.12934140861034393,
|
| 1678 |
+
"learning_rate": 4.635012847212748e-05,
|
| 1679 |
+
"loss": 0.1725,
|
| 1680 |
+
"num_input_tokens_seen": 15198192,
|
| 1681 |
+
"step": 209
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 3.4485981308411215,
|
| 1685 |
+
"grad_norm": 0.18388882279396057,
|
| 1686 |
+
"learning_rate": 4.6316004108852305e-05,
|
| 1687 |
+
"loss": 0.186,
|
| 1688 |
+
"num_input_tokens_seen": 15258432,
|
| 1689 |
+
"step": 210
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 3.4652128764278296,
|
| 1693 |
+
"grad_norm": 0.1766858547925949,
|
| 1694 |
+
"learning_rate": 4.628173364807171e-05,
|
| 1695 |
+
"loss": 0.2166,
|
| 1696 |
+
"num_input_tokens_seen": 15329600,
|
| 1697 |
+
"step": 211
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 3.4818276220145377,
|
| 1701 |
+
"grad_norm": 0.16214998066425323,
|
| 1702 |
+
"learning_rate": 4.6247317324671605e-05,
|
| 1703 |
+
"loss": 0.2038,
|
| 1704 |
+
"num_input_tokens_seen": 15407920,
|
| 1705 |
+
"step": 212
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 3.498442367601246,
|
| 1709 |
+
"grad_norm": 0.16933797299861908,
|
| 1710 |
+
"learning_rate": 4.6212755374537596e-05,
|
| 1711 |
+
"loss": 0.2017,
|
| 1712 |
+
"num_input_tokens_seen": 15479640,
|
| 1713 |
+
"step": 213
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 3.515057113187954,
|
| 1717 |
+
"grad_norm": 0.19472749531269073,
|
| 1718 |
+
"learning_rate": 4.617804803455344e-05,
|
| 1719 |
+
"loss": 0.2048,
|
| 1720 |
+
"num_input_tokens_seen": 15561960,
|
| 1721 |
+
"step": 214
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 3.5316718587746623,
|
| 1725 |
+
"grad_norm": 0.33335182070732117,
|
| 1726 |
+
"learning_rate": 4.614319554259934e-05,
|
| 1727 |
+
"loss": 0.2358,
|
| 1728 |
+
"num_input_tokens_seen": 15641440,
|
| 1729 |
+
"step": 215
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 3.5482866043613708,
|
| 1733 |
+
"grad_norm": 0.19587557017803192,
|
| 1734 |
+
"learning_rate": 4.610819813755038e-05,
|
| 1735 |
+
"loss": 0.2374,
|
| 1736 |
+
"num_input_tokens_seen": 15728872,
|
| 1737 |
+
"step": 216
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 3.564901349948079,
|
| 1741 |
+
"grad_norm": 0.19063518941402435,
|
| 1742 |
+
"learning_rate": 4.607305605927487e-05,
|
| 1743 |
+
"loss": 0.1919,
|
| 1744 |
+
"num_input_tokens_seen": 15798112,
|
| 1745 |
+
"step": 217
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 3.581516095534787,
|
| 1749 |
+
"grad_norm": 0.19598323106765747,
|
| 1750 |
+
"learning_rate": 4.6037769548632656e-05,
|
| 1751 |
+
"loss": 0.2583,
|
| 1752 |
+
"num_input_tokens_seen": 15865936,
|
| 1753 |
+
"step": 218
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 3.5981308411214954,
|
| 1757 |
+
"grad_norm": 0.18066690862178802,
|
| 1758 |
+
"learning_rate": 4.600233884747355e-05,
|
| 1759 |
+
"loss": 0.2337,
|
| 1760 |
+
"num_input_tokens_seen": 15941368,
|
| 1761 |
+
"step": 219
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 3.6147455867082035,
|
| 1765 |
+
"grad_norm": 0.16981899738311768,
|
| 1766 |
+
"learning_rate": 4.5966764198635606e-05,
|
| 1767 |
+
"loss": 0.1818,
|
| 1768 |
+
"num_input_tokens_seen": 16028208,
|
| 1769 |
+
"step": 220
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 3.6313603322949115,
|
| 1773 |
+
"grad_norm": 0.180410236120224,
|
| 1774 |
+
"learning_rate": 4.5931045845943474e-05,
|
| 1775 |
+
"loss": 0.1646,
|
| 1776 |
+
"num_input_tokens_seen": 16104408,
|
| 1777 |
+
"step": 221
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 3.64797507788162,
|
| 1781 |
+
"grad_norm": 0.19180680811405182,
|
| 1782 |
+
"learning_rate": 4.5895184034206765e-05,
|
| 1783 |
+
"loss": 0.3263,
|
| 1784 |
+
"num_input_tokens_seen": 16156800,
|
| 1785 |
+
"step": 222
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 3.664589823468328,
|
| 1789 |
+
"grad_norm": 0.16119280457496643,
|
| 1790 |
+
"learning_rate": 4.585917900921829e-05,
|
| 1791 |
+
"loss": 0.2636,
|
| 1792 |
+
"num_input_tokens_seen": 16256712,
|
| 1793 |
+
"step": 223
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 3.681204569055036,
|
| 1797 |
+
"grad_norm": 0.18559172749519348,
|
| 1798 |
+
"learning_rate": 4.5823031017752485e-05,
|
| 1799 |
+
"loss": 0.1759,
|
| 1800 |
+
"num_input_tokens_seen": 16330344,
|
| 1801 |
+
"step": 224
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 3.6978193146417446,
|
| 1805 |
+
"grad_norm": 0.17767880856990814,
|
| 1806 |
+
"learning_rate": 4.5786740307563636e-05,
|
| 1807 |
+
"loss": 0.196,
|
| 1808 |
+
"num_input_tokens_seen": 16399792,
|
| 1809 |
+
"step": 225
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 3.7144340602284527,
|
| 1813 |
+
"grad_norm": 0.17806987464427948,
|
| 1814 |
+
"learning_rate": 4.575030712738419e-05,
|
| 1815 |
+
"loss": 0.186,
|
| 1816 |
+
"num_input_tokens_seen": 16466368,
|
| 1817 |
+
"step": 226
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 3.7310488058151607,
|
| 1821 |
+
"grad_norm": 0.1952792853116989,
|
| 1822 |
+
"learning_rate": 4.571373172692309e-05,
|
| 1823 |
+
"loss": 0.1789,
|
| 1824 |
+
"num_input_tokens_seen": 16530976,
|
| 1825 |
+
"step": 227
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 3.7476635514018692,
|
| 1829 |
+
"grad_norm": 0.1774374544620514,
|
| 1830 |
+
"learning_rate": 4.567701435686404e-05,
|
| 1831 |
+
"loss": 0.1929,
|
| 1832 |
+
"num_input_tokens_seen": 16600216,
|
| 1833 |
+
"step": 228
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 3.7642782969885773,
|
| 1837 |
+
"grad_norm": 0.18798600137233734,
|
| 1838 |
+
"learning_rate": 4.5640155268863796e-05,
|
| 1839 |
+
"loss": 0.2268,
|
| 1840 |
+
"num_input_tokens_seen": 16673192,
|
| 1841 |
+
"step": 229
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 3.7808930425752854,
|
| 1845 |
+
"grad_norm": 0.2022520750761032,
|
| 1846 |
+
"learning_rate": 4.5603154715550386e-05,
|
| 1847 |
+
"loss": 0.1716,
|
| 1848 |
+
"num_input_tokens_seen": 16739912,
|
| 1849 |
+
"step": 230
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 3.797507788161994,
|
| 1853 |
+
"grad_norm": 0.15170948207378387,
|
| 1854 |
+
"learning_rate": 4.55660129505215e-05,
|
| 1855 |
+
"loss": 0.1844,
|
| 1856 |
+
"num_input_tokens_seen": 16834632,
|
| 1857 |
+
"step": 231
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 3.814122533748702,
|
| 1861 |
+
"grad_norm": 0.16655084490776062,
|
| 1862 |
+
"learning_rate": 4.5528730228342605e-05,
|
| 1863 |
+
"loss": 0.1899,
|
| 1864 |
+
"num_input_tokens_seen": 16914728,
|
| 1865 |
+
"step": 232
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.83073727933541,
|
| 1869 |
+
"grad_norm": 0.19025221467018127,
|
| 1870 |
+
"learning_rate": 4.549130680454532e-05,
|
| 1871 |
+
"loss": 0.2214,
|
| 1872 |
+
"num_input_tokens_seen": 17014304,
|
| 1873 |
+
"step": 233
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 3.8473520249221185,
|
| 1877 |
+
"grad_norm": 0.17126557230949402,
|
| 1878 |
+
"learning_rate": 4.545374293562559e-05,
|
| 1879 |
+
"loss": 0.2062,
|
| 1880 |
+
"num_input_tokens_seen": 17106664,
|
| 1881 |
+
"step": 234
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 3.8639667705088265,
|
| 1885 |
+
"grad_norm": 0.16162410378456116,
|
| 1886 |
+
"learning_rate": 4.541603887904198e-05,
|
| 1887 |
+
"loss": 0.2016,
|
| 1888 |
+
"num_input_tokens_seen": 17193744,
|
| 1889 |
+
"step": 235
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 3.8805815160955346,
|
| 1893 |
+
"grad_norm": 0.2067136913537979,
|
| 1894 |
+
"learning_rate": 4.537819489321386e-05,
|
| 1895 |
+
"loss": 0.1992,
|
| 1896 |
+
"num_input_tokens_seen": 17254656,
|
| 1897 |
+
"step": 236
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 3.897196261682243,
|
| 1901 |
+
"grad_norm": 0.200433611869812,
|
| 1902 |
+
"learning_rate": 4.534021123751968e-05,
|
| 1903 |
+
"loss": 0.1961,
|
| 1904 |
+
"num_input_tokens_seen": 17325896,
|
| 1905 |
+
"step": 237
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 3.913811007268951,
|
| 1909 |
+
"grad_norm": 0.2062034010887146,
|
| 1910 |
+
"learning_rate": 4.5302088172295156e-05,
|
| 1911 |
+
"loss": 0.2302,
|
| 1912 |
+
"num_input_tokens_seen": 17394424,
|
| 1913 |
+
"step": 238
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 3.930425752855659,
|
| 1917 |
+
"grad_norm": 0.1928798407316208,
|
| 1918 |
+
"learning_rate": 4.526382595883152e-05,
|
| 1919 |
+
"loss": 0.1846,
|
| 1920 |
+
"num_input_tokens_seen": 17456352,
|
| 1921 |
+
"step": 239
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 3.9470404984423677,
|
| 1925 |
+
"grad_norm": 0.2011859118938446,
|
| 1926 |
+
"learning_rate": 4.522542485937369e-05,
|
| 1927 |
+
"loss": 0.1879,
|
| 1928 |
+
"num_input_tokens_seen": 17519168,
|
| 1929 |
+
"step": 240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.9636552440290758,
|
| 1933 |
+
"grad_norm": 0.20441657304763794,
|
| 1934 |
+
"learning_rate": 4.51868851371185e-05,
|
| 1935 |
+
"loss": 0.206,
|
| 1936 |
+
"num_input_tokens_seen": 17585144,
|
| 1937 |
+
"step": 241
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 3.980269989615784,
|
| 1941 |
+
"grad_norm": 0.18314018845558167,
|
| 1942 |
+
"learning_rate": 4.5148207056212896e-05,
|
| 1943 |
+
"loss": 0.1676,
|
| 1944 |
+
"num_input_tokens_seen": 17662024,
|
| 1945 |
+
"step": 242
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 3.9968847352024923,
|
| 1949 |
+
"grad_norm": 0.21530692279338837,
|
| 1950 |
+
"learning_rate": 4.5109390881752114e-05,
|
| 1951 |
+
"loss": 0.1961,
|
| 1952 |
+
"num_input_tokens_seen": 17724360,
|
| 1953 |
+
"step": 243
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 4.0,
|
| 1957 |
+
"grad_norm": 0.38912200927734375,
|
| 1958 |
+
"learning_rate": 4.5070436879777865e-05,
|
| 1959 |
+
"loss": 0.185,
|
| 1960 |
+
"num_input_tokens_seen": 17746200,
|
| 1961 |
+
"step": 244
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 4.0166147455867085,
|
| 1965 |
+
"grad_norm": 0.15166164934635162,
|
| 1966 |
+
"learning_rate": 4.503134531727652e-05,
|
| 1967 |
+
"loss": 0.1674,
|
| 1968 |
+
"num_input_tokens_seen": 17830760,
|
| 1969 |
+
"step": 245
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 4.033229491173416,
|
| 1973 |
+
"grad_norm": 0.1999833583831787,
|
| 1974 |
+
"learning_rate": 4.499211646217727e-05,
|
| 1975 |
+
"loss": 0.1739,
|
| 1976 |
+
"num_input_tokens_seen": 17903840,
|
| 1977 |
+
"step": 246
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 4.049844236760125,
|
| 1981 |
+
"grad_norm": 0.2024000585079193,
|
| 1982 |
+
"learning_rate": 4.495275058335029e-05,
|
| 1983 |
+
"loss": 0.1753,
|
| 1984 |
+
"num_input_tokens_seen": 17990448,
|
| 1985 |
+
"step": 247
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 4.066458982346833,
|
| 1989 |
+
"grad_norm": 0.22637376189231873,
|
| 1990 |
+
"learning_rate": 4.491324795060491e-05,
|
| 1991 |
+
"loss": 0.1896,
|
| 1992 |
+
"num_input_tokens_seen": 18069520,
|
| 1993 |
+
"step": 248
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 4.083073727933541,
|
| 1997 |
+
"grad_norm": 0.24361123144626617,
|
| 1998 |
+
"learning_rate": 4.487360883468775e-05,
|
| 1999 |
+
"loss": 0.1688,
|
| 2000 |
+
"num_input_tokens_seen": 18129128,
|
| 2001 |
+
"step": 249
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 4.099688473520249,
|
| 2005 |
+
"grad_norm": 0.21949416399002075,
|
| 2006 |
+
"learning_rate": 4.4833833507280884e-05,
|
| 2007 |
+
"loss": 0.1928,
|
| 2008 |
+
"num_input_tokens_seen": 18202472,
|
| 2009 |
+
"step": 250
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 4.116303219106958,
|
| 2013 |
+
"grad_norm": 0.22039519250392914,
|
| 2014 |
+
"learning_rate": 4.4793922240999933e-05,
|
| 2015 |
+
"loss": 0.1737,
|
| 2016 |
+
"num_input_tokens_seen": 18267232,
|
| 2017 |
+
"step": 251
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 4.132917964693665,
|
| 2021 |
+
"grad_norm": 0.23173294961452484,
|
| 2022 |
+
"learning_rate": 4.4753875309392266e-05,
|
| 2023 |
+
"loss": 0.1883,
|
| 2024 |
+
"num_input_tokens_seen": 18325216,
|
| 2025 |
+
"step": 252
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 4.149532710280374,
|
| 2029 |
+
"grad_norm": 0.24100351333618164,
|
| 2030 |
+
"learning_rate": 4.471369298693505e-05,
|
| 2031 |
+
"loss": 0.2042,
|
| 2032 |
+
"num_input_tokens_seen": 18406184,
|
| 2033 |
+
"step": 253
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 4.166147455867082,
|
| 2037 |
+
"grad_norm": 0.1888919323682785,
|
| 2038 |
+
"learning_rate": 4.467337554903344e-05,
|
| 2039 |
+
"loss": 0.1656,
|
| 2040 |
+
"num_input_tokens_seen": 18481056,
|
| 2041 |
+
"step": 254
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 4.18276220145379,
|
| 2045 |
+
"grad_norm": 0.17849119007587433,
|
| 2046 |
+
"learning_rate": 4.463292327201862e-05,
|
| 2047 |
+
"loss": 0.1454,
|
| 2048 |
+
"num_input_tokens_seen": 18554864,
|
| 2049 |
+
"step": 255
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 4.1993769470404985,
|
| 2053 |
+
"grad_norm": 0.24600732326507568,
|
| 2054 |
+
"learning_rate": 4.4592336433146e-05,
|
| 2055 |
+
"loss": 0.2039,
|
| 2056 |
+
"num_input_tokens_seen": 18612120,
|
| 2057 |
+
"step": 256
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 4.215991692627207,
|
| 2061 |
+
"grad_norm": 0.23695628345012665,
|
| 2062 |
+
"learning_rate": 4.4551615310593195e-05,
|
| 2063 |
+
"loss": 0.2112,
|
| 2064 |
+
"num_input_tokens_seen": 18710408,
|
| 2065 |
+
"step": 257
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 4.232606438213915,
|
| 2069 |
+
"grad_norm": 0.2511826753616333,
|
| 2070 |
+
"learning_rate": 4.451076018345825e-05,
|
| 2071 |
+
"loss": 0.1831,
|
| 2072 |
+
"num_input_tokens_seen": 18769400,
|
| 2073 |
+
"step": 258
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 4.249221183800623,
|
| 2077 |
+
"grad_norm": 0.1971820890903473,
|
| 2078 |
+
"learning_rate": 4.4469771331757604e-05,
|
| 2079 |
+
"loss": 0.1722,
|
| 2080 |
+
"num_input_tokens_seen": 18849704,
|
| 2081 |
+
"step": 259
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 4.265835929387332,
|
| 2085 |
+
"grad_norm": 0.23203876614570618,
|
| 2086 |
+
"learning_rate": 4.442864903642428e-05,
|
| 2087 |
+
"loss": 0.1981,
|
| 2088 |
+
"num_input_tokens_seen": 18943328,
|
| 2089 |
+
"step": 260
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 4.282450674974039,
|
| 2093 |
+
"grad_norm": 0.23434185981750488,
|
| 2094 |
+
"learning_rate": 4.4387393579305865e-05,
|
| 2095 |
+
"loss": 0.2014,
|
| 2096 |
+
"num_input_tokens_seen": 19022536,
|
| 2097 |
+
"step": 261
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 4.299065420560748,
|
| 2101 |
+
"grad_norm": 0.2373885214328766,
|
| 2102 |
+
"learning_rate": 4.434600524316266e-05,
|
| 2103 |
+
"loss": 0.167,
|
| 2104 |
+
"num_input_tokens_seen": 19089200,
|
| 2105 |
+
"step": 262
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 4.315680166147456,
|
| 2109 |
+
"grad_norm": 0.20130722224712372,
|
| 2110 |
+
"learning_rate": 4.430448431166567e-05,
|
| 2111 |
+
"loss": 0.2747,
|
| 2112 |
+
"num_input_tokens_seen": 19171216,
|
| 2113 |
+
"step": 263
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 4.332294911734164,
|
| 2117 |
+
"grad_norm": 0.17947593331336975,
|
| 2118 |
+
"learning_rate": 4.426283106939474e-05,
|
| 2119 |
+
"loss": 0.1508,
|
| 2120 |
+
"num_input_tokens_seen": 19271872,
|
| 2121 |
+
"step": 264
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 4.348909657320872,
|
| 2125 |
+
"grad_norm": 0.23321041464805603,
|
| 2126 |
+
"learning_rate": 4.4221045801836494e-05,
|
| 2127 |
+
"loss": 0.2585,
|
| 2128 |
+
"num_input_tokens_seen": 19342984,
|
| 2129 |
+
"step": 265
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 4.365524402907581,
|
| 2133 |
+
"grad_norm": 0.26581740379333496,
|
| 2134 |
+
"learning_rate": 4.41791287953825e-05,
|
| 2135 |
+
"loss": 0.1789,
|
| 2136 |
+
"num_input_tokens_seen": 19391640,
|
| 2137 |
+
"step": 266
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 4.382139148494288,
|
| 2141 |
+
"grad_norm": 0.20715415477752686,
|
| 2142 |
+
"learning_rate": 4.4137080337327205e-05,
|
| 2143 |
+
"loss": 0.1953,
|
| 2144 |
+
"num_input_tokens_seen": 19463232,
|
| 2145 |
+
"step": 267
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 4.398753894080997,
|
| 2149 |
+
"grad_norm": 0.20641866326332092,
|
| 2150 |
+
"learning_rate": 4.4094900715866064e-05,
|
| 2151 |
+
"loss": 0.1752,
|
| 2152 |
+
"num_input_tokens_seen": 19523728,
|
| 2153 |
+
"step": 268
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 4.415368639667705,
|
| 2157 |
+
"grad_norm": 0.23343385756015778,
|
| 2158 |
+
"learning_rate": 4.4052590220093446e-05,
|
| 2159 |
+
"loss": 0.1904,
|
| 2160 |
+
"num_input_tokens_seen": 19598960,
|
| 2161 |
+
"step": 269
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 4.431983385254413,
|
| 2165 |
+
"grad_norm": 0.20117436349391937,
|
| 2166 |
+
"learning_rate": 4.401014914000078e-05,
|
| 2167 |
+
"loss": 0.1801,
|
| 2168 |
+
"num_input_tokens_seen": 19666136,
|
| 2169 |
+
"step": 270
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 4.4485981308411215,
|
| 2173 |
+
"grad_norm": 0.24009813368320465,
|
| 2174 |
+
"learning_rate": 4.3967577766474455e-05,
|
| 2175 |
+
"loss": 0.1798,
|
| 2176 |
+
"num_input_tokens_seen": 19728600,
|
| 2177 |
+
"step": 271
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 4.46521287642783,
|
| 2181 |
+
"grad_norm": 0.2242031991481781,
|
| 2182 |
+
"learning_rate": 4.3924876391293915e-05,
|
| 2183 |
+
"loss": 0.2221,
|
| 2184 |
+
"num_input_tokens_seen": 19801032,
|
| 2185 |
+
"step": 272
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 4.481827622014538,
|
| 2189 |
+
"grad_norm": 0.22890391945838928,
|
| 2190 |
+
"learning_rate": 4.3882045307129594e-05,
|
| 2191 |
+
"loss": 0.1906,
|
| 2192 |
+
"num_input_tokens_seen": 19885496,
|
| 2193 |
+
"step": 273
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 4.498442367601246,
|
| 2197 |
+
"grad_norm": 0.21996937692165375,
|
| 2198 |
+
"learning_rate": 4.383908480754095e-05,
|
| 2199 |
+
"loss": 0.1775,
|
| 2200 |
+
"num_input_tokens_seen": 19952072,
|
| 2201 |
+
"step": 274
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 4.515057113187955,
|
| 2205 |
+
"grad_norm": 0.1860388070344925,
|
| 2206 |
+
"learning_rate": 4.379599518697444e-05,
|
| 2207 |
+
"loss": 0.1593,
|
| 2208 |
+
"num_input_tokens_seen": 20026536,
|
| 2209 |
+
"step": 275
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 4.531671858774662,
|
| 2213 |
+
"grad_norm": 0.20987707376480103,
|
| 2214 |
+
"learning_rate": 4.375277674076149e-05,
|
| 2215 |
+
"loss": 0.1409,
|
| 2216 |
+
"num_input_tokens_seen": 20079112,
|
| 2217 |
+
"step": 276
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 4.548286604361371,
|
| 2221 |
+
"grad_norm": 0.21347324550151825,
|
| 2222 |
+
"learning_rate": 4.3709429765116504e-05,
|
| 2223 |
+
"loss": 0.2701,
|
| 2224 |
+
"num_input_tokens_seen": 20144264,
|
| 2225 |
+
"step": 277
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 4.564901349948079,
|
| 2229 |
+
"grad_norm": 0.27563896775245667,
|
| 2230 |
+
"learning_rate": 4.366595455713479e-05,
|
| 2231 |
+
"loss": 0.1856,
|
| 2232 |
+
"num_input_tokens_seen": 20207568,
|
| 2233 |
+
"step": 278
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 4.581516095534787,
|
| 2237 |
+
"grad_norm": 0.21850791573524475,
|
| 2238 |
+
"learning_rate": 4.3622351414790554e-05,
|
| 2239 |
+
"loss": 0.2204,
|
| 2240 |
+
"num_input_tokens_seen": 20292376,
|
| 2241 |
+
"step": 279
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 4.598130841121495,
|
| 2245 |
+
"grad_norm": 0.19672711193561554,
|
| 2246 |
+
"learning_rate": 4.357862063693486e-05,
|
| 2247 |
+
"loss": 0.1397,
|
| 2248 |
+
"num_input_tokens_seen": 20383048,
|
| 2249 |
+
"step": 280
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 4.614745586708204,
|
| 2253 |
+
"grad_norm": 0.23507343232631683,
|
| 2254 |
+
"learning_rate": 4.353476252329356e-05,
|
| 2255 |
+
"loss": 0.1655,
|
| 2256 |
+
"num_input_tokens_seen": 20463376,
|
| 2257 |
+
"step": 281
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 4.6313603322949115,
|
| 2261 |
+
"grad_norm": 0.23900464177131653,
|
| 2262 |
+
"learning_rate": 4.349077737446525e-05,
|
| 2263 |
+
"loss": 0.1511,
|
| 2264 |
+
"num_input_tokens_seen": 20537808,
|
| 2265 |
+
"step": 282
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 4.64797507788162,
|
| 2269 |
+
"grad_norm": 0.2231033891439438,
|
| 2270 |
+
"learning_rate": 4.344666549191921e-05,
|
| 2271 |
+
"loss": 0.1783,
|
| 2272 |
+
"num_input_tokens_seen": 20605496,
|
| 2273 |
+
"step": 283
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 4.6645898234683285,
|
| 2277 |
+
"grad_norm": 0.20772908627986908,
|
| 2278 |
+
"learning_rate": 4.3402427177993366e-05,
|
| 2279 |
+
"loss": 0.2135,
|
| 2280 |
+
"num_input_tokens_seen": 20692096,
|
| 2281 |
+
"step": 284
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 4.681204569055036,
|
| 2285 |
+
"grad_norm": 0.24927115440368652,
|
| 2286 |
+
"learning_rate": 4.335806273589214e-05,
|
| 2287 |
+
"loss": 0.1919,
|
| 2288 |
+
"num_input_tokens_seen": 20762800,
|
| 2289 |
+
"step": 285
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 4.697819314641745,
|
| 2293 |
+
"grad_norm": 0.2112305462360382,
|
| 2294 |
+
"learning_rate": 4.3313572469684474e-05,
|
| 2295 |
+
"loss": 0.1546,
|
| 2296 |
+
"num_input_tokens_seen": 20831584,
|
| 2297 |
+
"step": 286
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 4.714434060228453,
|
| 2301 |
+
"grad_norm": 0.22639551758766174,
|
| 2302 |
+
"learning_rate": 4.326895668430166e-05,
|
| 2303 |
+
"loss": 0.124,
|
| 2304 |
+
"num_input_tokens_seen": 20897320,
|
| 2305 |
+
"step": 287
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 4.731048805815161,
|
| 2309 |
+
"grad_norm": 0.2295934110879898,
|
| 2310 |
+
"learning_rate": 4.3224215685535294e-05,
|
| 2311 |
+
"loss": 0.1639,
|
| 2312 |
+
"num_input_tokens_seen": 20966136,
|
| 2313 |
+
"step": 288
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 4.747663551401869,
|
| 2317 |
+
"grad_norm": 0.2341577112674713,
|
| 2318 |
+
"learning_rate": 4.317934978003517e-05,
|
| 2319 |
+
"loss": 0.1584,
|
| 2320 |
+
"num_input_tokens_seen": 21034800,
|
| 2321 |
+
"step": 289
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 4.764278296988578,
|
| 2325 |
+
"grad_norm": 0.2542404234409332,
|
| 2326 |
+
"learning_rate": 4.313435927530719e-05,
|
| 2327 |
+
"loss": 0.1918,
|
| 2328 |
+
"num_input_tokens_seen": 21098672,
|
| 2329 |
+
"step": 290
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 4.780893042575285,
|
| 2333 |
+
"grad_norm": 0.23311223089694977,
|
| 2334 |
+
"learning_rate": 4.3089244479711236e-05,
|
| 2335 |
+
"loss": 0.1597,
|
| 2336 |
+
"num_input_tokens_seen": 21177632,
|
| 2337 |
+
"step": 291
|
| 2338 |
+
},
|
| 2339 |
+
{
|
| 2340 |
+
"epoch": 4.797507788161994,
|
| 2341 |
+
"grad_norm": 0.2642923593521118,
|
| 2342 |
+
"learning_rate": 4.304400570245906e-05,
|
| 2343 |
+
"loss": 0.1847,
|
| 2344 |
+
"num_input_tokens_seen": 21240896,
|
| 2345 |
+
"step": 292
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 4.814122533748702,
|
| 2349 |
+
"grad_norm": 0.18841278553009033,
|
| 2350 |
+
"learning_rate": 4.299864325361217e-05,
|
| 2351 |
+
"loss": 0.1472,
|
| 2352 |
+
"num_input_tokens_seen": 21322984,
|
| 2353 |
+
"step": 293
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 4.83073727933541,
|
| 2357 |
+
"grad_norm": 0.22440434992313385,
|
| 2358 |
+
"learning_rate": 4.295315744407972e-05,
|
| 2359 |
+
"loss": 0.1607,
|
| 2360 |
+
"num_input_tokens_seen": 21389128,
|
| 2361 |
+
"step": 294
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 4.8473520249221185,
|
| 2365 |
+
"grad_norm": 0.22145289182662964,
|
| 2366 |
+
"learning_rate": 4.290754858561637e-05,
|
| 2367 |
+
"loss": 0.1851,
|
| 2368 |
+
"num_input_tokens_seen": 21469912,
|
| 2369 |
+
"step": 295
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 4.863966770508826,
|
| 2373 |
+
"grad_norm": 0.22817087173461914,
|
| 2374 |
+
"learning_rate": 4.2861816990820084e-05,
|
| 2375 |
+
"loss": 0.1531,
|
| 2376 |
+
"num_input_tokens_seen": 21540320,
|
| 2377 |
+
"step": 296
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 4.880581516095535,
|
| 2381 |
+
"grad_norm": 0.22014038264751434,
|
| 2382 |
+
"learning_rate": 4.281596297313013e-05,
|
| 2383 |
+
"loss": 0.1815,
|
| 2384 |
+
"num_input_tokens_seen": 21626312,
|
| 2385 |
+
"step": 297
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 4.897196261682243,
|
| 2389 |
+
"grad_norm": 0.2234148383140564,
|
| 2390 |
+
"learning_rate": 4.2769986846824815e-05,
|
| 2391 |
+
"loss": 0.1667,
|
| 2392 |
+
"num_input_tokens_seen": 21702792,
|
| 2393 |
+
"step": 298
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 4.913811007268951,
|
| 2397 |
+
"grad_norm": 0.2851375341415405,
|
| 2398 |
+
"learning_rate": 4.272388892701934e-05,
|
| 2399 |
+
"loss": 0.1805,
|
| 2400 |
+
"num_input_tokens_seen": 21771880,
|
| 2401 |
+
"step": 299
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 4.930425752855659,
|
| 2405 |
+
"grad_norm": 0.2221265286207199,
|
| 2406 |
+
"learning_rate": 4.267766952966369e-05,
|
| 2407 |
+
"loss": 0.1653,
|
| 2408 |
+
"num_input_tokens_seen": 21844024,
|
| 2409 |
+
"step": 300
|
| 2410 |
+
}
|
| 2411 |
+
],
|
| 2412 |
+
"logging_steps": 1.0,
|
| 2413 |
+
"max_steps": 1200,
|
| 2414 |
+
"num_input_tokens_seen": 21844024,
|
| 2415 |
+
"num_train_epochs": 20,
|
| 2416 |
+
"save_steps": 60,
|
| 2417 |
+
"stateful_callbacks": {
|
| 2418 |
+
"TrainerControl": {
|
| 2419 |
+
"args": {
|
| 2420 |
+
"should_epoch_stop": false,
|
| 2421 |
+
"should_evaluate": false,
|
| 2422 |
+
"should_log": false,
|
| 2423 |
+
"should_save": true,
|
| 2424 |
+
"should_training_stop": false
|
| 2425 |
+
},
|
| 2426 |
+
"attributes": {}
|
| 2427 |
+
}
|
| 2428 |
+
},
|
| 2429 |
+
"total_flos": 1.8427983967677317e+18,
|
| 2430 |
+
"train_batch_size": 1,
|
| 2431 |
+
"trial_name": null,
|
| 2432 |
+
"trial_params": null
|
| 2433 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ead4a6550d360b2767d5cafb708fc1265f2158252d104b64f05a5368cafaafc9
|
| 3 |
+
size 5752
|
checkpoint-360/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-360/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:849be0d09248ef082e38d807e519e16a189728cfeb3fd0e29011d16947a21c12
|
| 3 |
+
size 275341720
|
checkpoint-360/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fcafba873e0ca9f4eaab1bd1fab65dad57cf9297bd73a75e624bd915eb77e6b
|
| 3 |
+
size 14512
|
checkpoint-360/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e96e34c0423f2985fb22e69c08a1a92f556220c9f513f52d85d318dd4a18989
|
| 3 |
+
size 1064
|
checkpoint-360/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-420/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-420/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad31d25dde5055b4eca78bf7b8294faab339c2b5032e8aa6bec19cac4d093d44
|
| 3 |
+
size 275341720
|
checkpoint-420/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
checkpoint-420/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:432a613381824a4c965b77d67bcbde55182511838e8b003c10f77144a53dfe44
|
| 3 |
+
size 551070514
|
checkpoint-420/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4268749f0efa61d0627aa4290c67eb20b74e92ffbe2a5ff1e8fed44f37c87e4c
|
| 3 |
+
size 14512
|
checkpoint-420/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
checkpoint-480/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-480/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c33746e890bdf8846ec109e4475cfb285658db6b8eef8bc77bb2f26f1cb105e
|
| 3 |
+
size 275341720
|
checkpoint-480/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-480/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e60585c80c74a89fe69a16f6d36250e35aadca7c40ac738c0aa3de0b44a7fcb3
|
| 3 |
+
size 551070514
|
checkpoint-480/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f1649c0e1d5f5e61fa69910ec08803444768d7f19c741470b603d80af62d781
|
| 3 |
+
size 1064
|
checkpoint-480/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|