Upload folder using huggingface_hub
Browse files- checkpoint-17440/merges.txt +0 -0
- checkpoint-17440/model.safetensors +3 -0
- checkpoint-17440/optimizer.pt +3 -0
- checkpoint-17440/rng_state.pth +3 -0
- checkpoint-17440/scaler.pt +3 -0
- checkpoint-17440/scheduler.pt +3 -0
- checkpoint-17440/special_tokens_map.json +51 -0
- checkpoint-17440/tokenizer.json +0 -0
- checkpoint-17440/tokenizer_config.json +58 -0
- checkpoint-17440/trainer_state.json +1300 -0
- checkpoint-17440/training_args.bin +3 -0
- checkpoint-17440/vocab.json +0 -0
- checkpoint-4360/merges.txt +0 -0
- checkpoint-4360/model.safetensors +3 -0
- checkpoint-4360/optimizer.pt +3 -0
- checkpoint-4360/rng_state.pth +3 -0
- checkpoint-4360/scaler.pt +3 -0
- checkpoint-4360/scheduler.pt +3 -0
- checkpoint-4360/special_tokens_map.json +51 -0
- checkpoint-4360/tokenizer.json +0 -0
- checkpoint-4360/tokenizer_config.json +58 -0
- checkpoint-4360/trainer_state.json +347 -0
- checkpoint-4360/training_args.bin +3 -0
- checkpoint-4360/vocab.json +0 -0
- eval_metrics.json +11 -0
- runs/Jul26_05-00-38_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753506039.ip-172-31-31-181.ap-northeast-2.compute.internal.3768.0 +3 -0
- runs/Jul26_05-06-05_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753506367.ip-172-31-31-181.ap-northeast-2.compute.internal.3930.0 +3 -0
- runs/Jul26_05-10-49_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753506650.ip-172-31-31-181.ap-northeast-2.compute.internal.4146.0 +3 -0
- runs/Jul26_05-43-11_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753508592.ip-172-31-31-181.ap-northeast-2.compute.internal.3507.0 +3 -0
- runs/Jul26_05-45-04_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753508706.ip-172-31-31-181.ap-northeast-2.compute.internal.3608.0 +3 -0
- runs/Jul26_05-47-54_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753508876.ip-172-31-31-181.ap-northeast-2.compute.internal.3707.0 +3 -0
- runs/Jul26_05-54-27_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753509268.ip-172-31-31-181.ap-northeast-2.compute.internal.3990.0 +3 -0
- runs/Jul26_05-56-42_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753509403.ip-172-31-31-181.ap-northeast-2.compute.internal.4124.0 +3 -0
- runs/Jul26_05-56-42_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753534536.ip-172-31-31-181.ap-northeast-2.compute.internal.4124.1 +3 -0
checkpoint-17440/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-17440/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:208a9831c51ba0e41344cb5b3e9fed7ae49bb6a7902e5ca90ee9c4af4641aea8
|
| 3 |
+
size 498612808
|
checkpoint-17440/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2394db977c61f430ba3dd2952a1bf1a34d7f96a55d65e9f31e11f61ae62fafa
|
| 3 |
+
size 992619531
|
checkpoint-17440/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72fbbe3d7d60cafa27abcdf57f3860ff44626321d616524c7e6876819f8c68c4
|
| 3 |
+
size 14645
|
checkpoint-17440/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f21a0f645367961ee6fda5d7508429987a81410aae69b6d07afcfecd7e24e9b3
|
| 3 |
+
size 1383
|
checkpoint-17440/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a37b859070b59ed635492015b80a9bce86be62e57eaced46418484406f006c55
|
| 3 |
+
size 1465
|
checkpoint-17440/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-17440/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-17440/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-17440/trainer_state.json
ADDED
|
@@ -0,0 +1,1300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 4360,
|
| 3 |
+
"best_metric": 1.0,
|
| 4 |
+
"best_model_checkpoint": "gcbert_ckpt/checkpoint-4360",
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 17440,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.022938410368161487,
|
| 14 |
+
"grad_norm": 29.002798080444336,
|
| 15 |
+
"learning_rate": 2.809633027522936e-06,
|
| 16 |
+
"loss": 1.1878,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.045876820736322974,
|
| 21 |
+
"grad_norm": 68.14753723144531,
|
| 22 |
+
"learning_rate": 5.676605504587156e-06,
|
| 23 |
+
"loss": 0.6556,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06881523110448445,
|
| 28 |
+
"grad_norm": 54.466773986816406,
|
| 29 |
+
"learning_rate": 8.543577981651376e-06,
|
| 30 |
+
"loss": 0.288,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09175364147264595,
|
| 35 |
+
"grad_norm": 0.0029387406539171934,
|
| 36 |
+
"learning_rate": 1.1410550458715597e-05,
|
| 37 |
+
"loss": 0.0993,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11469205184080743,
|
| 42 |
+
"grad_norm": 0.00012727684224955738,
|
| 43 |
+
"learning_rate": 1.4277522935779817e-05,
|
| 44 |
+
"loss": 0.0,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1376304622089689,
|
| 49 |
+
"grad_norm": 0.0007764559122733772,
|
| 50 |
+
"learning_rate": 1.714449541284404e-05,
|
| 51 |
+
"loss": 0.0,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1605688725771304,
|
| 56 |
+
"grad_norm": 7.87975950515829e-05,
|
| 57 |
+
"learning_rate": 2.0011467889908257e-05,
|
| 58 |
+
"loss": 0.0,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1835072829452919,
|
| 63 |
+
"grad_norm": 0.0004955148906446993,
|
| 64 |
+
"learning_rate": 2.2878440366972478e-05,
|
| 65 |
+
"loss": 0.0,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2064456933134534,
|
| 70 |
+
"grad_norm": 0.00011743771756300703,
|
| 71 |
+
"learning_rate": 2.57454128440367e-05,
|
| 72 |
+
"loss": 0.0,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.22938410368161485,
|
| 77 |
+
"grad_norm": 0.0005010354216210544,
|
| 78 |
+
"learning_rate": 2.861238532110092e-05,
|
| 79 |
+
"loss": 0.0,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.25232251404977635,
|
| 84 |
+
"grad_norm": 0.00021343142725527287,
|
| 85 |
+
"learning_rate": 3.147935779816514e-05,
|
| 86 |
+
"loss": 0.0,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.2752609244179378,
|
| 91 |
+
"grad_norm": 0.00011905051360372454,
|
| 92 |
+
"learning_rate": 3.434633027522936e-05,
|
| 93 |
+
"loss": 0.0,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.29819933478609933,
|
| 98 |
+
"grad_norm": 0.00038216536631807685,
|
| 99 |
+
"learning_rate": 3.7213302752293576e-05,
|
| 100 |
+
"loss": 0.0,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3211377451542608,
|
| 105 |
+
"grad_norm": 4.422829078976065e-05,
|
| 106 |
+
"learning_rate": 4.00802752293578e-05,
|
| 107 |
+
"loss": 0.0,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3440761555224223,
|
| 112 |
+
"grad_norm": 0.0002208059886470437,
|
| 113 |
+
"learning_rate": 4.2947247706422025e-05,
|
| 114 |
+
"loss": 0.0,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.3670145658905838,
|
| 119 |
+
"grad_norm": 5.1115232054144144e-05,
|
| 120 |
+
"learning_rate": 4.581422018348624e-05,
|
| 121 |
+
"loss": 0.0,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.38995297625874525,
|
| 126 |
+
"grad_norm": 7.042491051834077e-05,
|
| 127 |
+
"learning_rate": 4.868119266055046e-05,
|
| 128 |
+
"loss": 0.0,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4128913866269068,
|
| 133 |
+
"grad_norm": 3.786469824262895e-05,
|
| 134 |
+
"learning_rate": 4.982798165137615e-05,
|
| 135 |
+
"loss": 0.0,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.43582979699506824,
|
| 140 |
+
"grad_norm": 1.468727168685291e-05,
|
| 141 |
+
"learning_rate": 4.950942915392457e-05,
|
| 142 |
+
"loss": 0.0,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4587682073632297,
|
| 147 |
+
"grad_norm": 3.0084795071161352e-05,
|
| 148 |
+
"learning_rate": 4.919087665647299e-05,
|
| 149 |
+
"loss": 0.0,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.48170661773139123,
|
| 154 |
+
"grad_norm": 2.5331471988465637e-05,
|
| 155 |
+
"learning_rate": 4.887232415902141e-05,
|
| 156 |
+
"loss": 0.0,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.5046450280995527,
|
| 161 |
+
"grad_norm": 2.618041617097333e-05,
|
| 162 |
+
"learning_rate": 4.855377166156983e-05,
|
| 163 |
+
"loss": 0.0,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5275834384677142,
|
| 168 |
+
"grad_norm": 2.4747334464336745e-05,
|
| 169 |
+
"learning_rate": 4.823521916411825e-05,
|
| 170 |
+
"loss": 0.0,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5505218488358756,
|
| 175 |
+
"grad_norm": 1.4968503819545731e-05,
|
| 176 |
+
"learning_rate": 4.791666666666667e-05,
|
| 177 |
+
"loss": 0.0,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5734602592040372,
|
| 182 |
+
"grad_norm": 0.00038964845589362085,
|
| 183 |
+
"learning_rate": 4.759811416921509e-05,
|
| 184 |
+
"loss": 0.0,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5963986695721987,
|
| 189 |
+
"grad_norm": 2.8935370210092515e-05,
|
| 190 |
+
"learning_rate": 4.7279561671763515e-05,
|
| 191 |
+
"loss": 0.0,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6193370799403601,
|
| 196 |
+
"grad_norm": 8.388165042561013e-06,
|
| 197 |
+
"learning_rate": 4.6961009174311924e-05,
|
| 198 |
+
"loss": 0.0,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6422754903085216,
|
| 203 |
+
"grad_norm": 1.768140464264434e-05,
|
| 204 |
+
"learning_rate": 4.664245667686035e-05,
|
| 205 |
+
"loss": 0.0,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6652139006766831,
|
| 210 |
+
"grad_norm": 1.36974013003055e-05,
|
| 211 |
+
"learning_rate": 4.6323904179408764e-05,
|
| 212 |
+
"loss": 0.0,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6881523110448446,
|
| 217 |
+
"grad_norm": 9.414131454832386e-06,
|
| 218 |
+
"learning_rate": 4.600535168195719e-05,
|
| 219 |
+
"loss": 0.0,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.7110907214130061,
|
| 224 |
+
"grad_norm": 4.622045162250288e-05,
|
| 225 |
+
"learning_rate": 4.568679918450561e-05,
|
| 226 |
+
"loss": 0.0,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.7340291317811676,
|
| 231 |
+
"grad_norm": 2.692650923563633e-05,
|
| 232 |
+
"learning_rate": 4.536824668705403e-05,
|
| 233 |
+
"loss": 0.0,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.756967542149329,
|
| 238 |
+
"grad_norm": 1.0936350008705631e-05,
|
| 239 |
+
"learning_rate": 4.504969418960245e-05,
|
| 240 |
+
"loss": 0.0,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.7799059525174905,
|
| 245 |
+
"grad_norm": 5.966558546788292e-06,
|
| 246 |
+
"learning_rate": 4.473114169215087e-05,
|
| 247 |
+
"loss": 0.0,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.802844362885652,
|
| 252 |
+
"grad_norm": 9.507278264209162e-06,
|
| 253 |
+
"learning_rate": 4.441258919469929e-05,
|
| 254 |
+
"loss": 0.0,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.8257827732538136,
|
| 259 |
+
"grad_norm": 1.0006630873249378e-05,
|
| 260 |
+
"learning_rate": 4.409403669724771e-05,
|
| 261 |
+
"loss": 0.0,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.848721183621975,
|
| 266 |
+
"grad_norm": 5.595240509137511e-06,
|
| 267 |
+
"learning_rate": 4.377548419979613e-05,
|
| 268 |
+
"loss": 0.0,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.8716595939901365,
|
| 273 |
+
"grad_norm": 8.78509945323458e-06,
|
| 274 |
+
"learning_rate": 4.3456931702344547e-05,
|
| 275 |
+
"loss": 0.0,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.894598004358298,
|
| 280 |
+
"grad_norm": 1.4489376553683542e-05,
|
| 281 |
+
"learning_rate": 4.313837920489297e-05,
|
| 282 |
+
"loss": 0.0,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.9175364147264594,
|
| 287 |
+
"grad_norm": 0.0006358507671393454,
|
| 288 |
+
"learning_rate": 4.281982670744139e-05,
|
| 289 |
+
"loss": 0.0,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.940474825094621,
|
| 294 |
+
"grad_norm": 2.2141068257042207e-05,
|
| 295 |
+
"learning_rate": 4.250127420998981e-05,
|
| 296 |
+
"loss": 0.0,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.9634132354627825,
|
| 301 |
+
"grad_norm": 2.3798056645318866e-06,
|
| 302 |
+
"learning_rate": 4.2182721712538226e-05,
|
| 303 |
+
"loss": 0.0,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9863516458309439,
|
| 308 |
+
"grad_norm": 2.4955927074188367e-05,
|
| 309 |
+
"learning_rate": 4.186416921508665e-05,
|
| 310 |
+
"loss": 0.0,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0,
|
| 315 |
+
"eval_accuracy": 1.0,
|
| 316 |
+
"eval_f1": 1.0,
|
| 317 |
+
"eval_loss": 3.4182854463660206e-11,
|
| 318 |
+
"eval_precision": 1.0,
|
| 319 |
+
"eval_recall": 1.0,
|
| 320 |
+
"eval_runtime": 342.7946,
|
| 321 |
+
"eval_samples_per_second": 50.867,
|
| 322 |
+
"eval_steps_per_second": 3.18,
|
| 323 |
+
"step": 4360
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.0091753641472645,
|
| 327 |
+
"grad_norm": 2.645613676577341e-06,
|
| 328 |
+
"learning_rate": 4.1545616717635066e-05,
|
| 329 |
+
"loss": 0.0,
|
| 330 |
+
"step": 4400
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.032113774515426,
|
| 334 |
+
"grad_norm": 1.391179011989152e-05,
|
| 335 |
+
"learning_rate": 4.122706422018349e-05,
|
| 336 |
+
"loss": 0.0,
|
| 337 |
+
"step": 4500
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.0550521848835877,
|
| 341 |
+
"grad_norm": 6.799902621423826e-06,
|
| 342 |
+
"learning_rate": 4.0908511722731906e-05,
|
| 343 |
+
"loss": 0.0,
|
| 344 |
+
"step": 4600
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.077990595251749,
|
| 348 |
+
"grad_norm": 5.317841896612663e-06,
|
| 349 |
+
"learning_rate": 4.058995922528033e-05,
|
| 350 |
+
"loss": 0.0,
|
| 351 |
+
"step": 4700
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.1009290056199106,
|
| 355 |
+
"grad_norm": 6.453754849644611e-06,
|
| 356 |
+
"learning_rate": 4.0271406727828745e-05,
|
| 357 |
+
"loss": 0.0,
|
| 358 |
+
"step": 4800
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.123867415988072,
|
| 362 |
+
"grad_norm": 3.003899337272742e-06,
|
| 363 |
+
"learning_rate": 3.995285423037717e-05,
|
| 364 |
+
"loss": 0.0,
|
| 365 |
+
"step": 4900
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.1468058263562335,
|
| 369 |
+
"grad_norm": 5.224228516453877e-06,
|
| 370 |
+
"learning_rate": 3.9634301732925585e-05,
|
| 371 |
+
"loss": 0.0,
|
| 372 |
+
"step": 5000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.169744236724395,
|
| 376 |
+
"grad_norm": 2.482443960616365e-06,
|
| 377 |
+
"learning_rate": 3.931574923547401e-05,
|
| 378 |
+
"loss": 0.0,
|
| 379 |
+
"step": 5100
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.1926826470925564,
|
| 383 |
+
"grad_norm": 1.988922804230242e-06,
|
| 384 |
+
"learning_rate": 3.899719673802243e-05,
|
| 385 |
+
"loss": 0.0,
|
| 386 |
+
"step": 5200
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.215621057460718,
|
| 390 |
+
"grad_norm": 2.143744268323644e-06,
|
| 391 |
+
"learning_rate": 3.867864424057085e-05,
|
| 392 |
+
"loss": 0.0,
|
| 393 |
+
"step": 5300
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.2385594678288794,
|
| 397 |
+
"grad_norm": 5.1592205636552535e-06,
|
| 398 |
+
"learning_rate": 3.836009174311927e-05,
|
| 399 |
+
"loss": 0.0,
|
| 400 |
+
"step": 5400
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.261497878197041,
|
| 404 |
+
"grad_norm": 3.7546260500676e-06,
|
| 405 |
+
"learning_rate": 3.804153924566769e-05,
|
| 406 |
+
"loss": 0.0,
|
| 407 |
+
"step": 5500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.2844362885652023,
|
| 411 |
+
"grad_norm": 2.9266414003359387e-06,
|
| 412 |
+
"learning_rate": 3.772298674821611e-05,
|
| 413 |
+
"loss": 0.0,
|
| 414 |
+
"step": 5600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.3073746989333639,
|
| 418 |
+
"grad_norm": 9.482760106038768e-06,
|
| 419 |
+
"learning_rate": 3.740443425076453e-05,
|
| 420 |
+
"loss": 0.0,
|
| 421 |
+
"step": 5700
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.3303131093015255,
|
| 425 |
+
"grad_norm": 5.139393579156604e-06,
|
| 426 |
+
"learning_rate": 3.7085881753312944e-05,
|
| 427 |
+
"loss": 0.0,
|
| 428 |
+
"step": 5800
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.3532515196696868,
|
| 432 |
+
"grad_norm": 1.1174703104188666e-05,
|
| 433 |
+
"learning_rate": 3.676732925586137e-05,
|
| 434 |
+
"loss": 0.0,
|
| 435 |
+
"step": 5900
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.3761899300378484,
|
| 439 |
+
"grad_norm": 1.985909420909593e-06,
|
| 440 |
+
"learning_rate": 3.6448776758409784e-05,
|
| 441 |
+
"loss": 0.0,
|
| 442 |
+
"step": 6000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.3991283404060098,
|
| 446 |
+
"grad_norm": 9.205145761370659e-05,
|
| 447 |
+
"learning_rate": 3.613022426095821e-05,
|
| 448 |
+
"loss": 0.0,
|
| 449 |
+
"step": 6100
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.4220667507741713,
|
| 453 |
+
"grad_norm": 4.935003289574524e-06,
|
| 454 |
+
"learning_rate": 3.5811671763506624e-05,
|
| 455 |
+
"loss": 0.0,
|
| 456 |
+
"step": 6200
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.445005161142333,
|
| 460 |
+
"grad_norm": 1.7747262290868093e-06,
|
| 461 |
+
"learning_rate": 3.549630479102956e-05,
|
| 462 |
+
"loss": 0.002,
|
| 463 |
+
"step": 6300
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 1.4679435715104943,
|
| 467 |
+
"grad_norm": 2.3939119273563847e-06,
|
| 468 |
+
"learning_rate": 3.517775229357798e-05,
|
| 469 |
+
"loss": 0.0,
|
| 470 |
+
"step": 6400
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.4908819818786558,
|
| 474 |
+
"grad_norm": 1.2233704183017835e-06,
|
| 475 |
+
"learning_rate": 3.48591997961264e-05,
|
| 476 |
+
"loss": 0.0,
|
| 477 |
+
"step": 6500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.5138203922468172,
|
| 481 |
+
"grad_norm": 1.0319820830773097e-05,
|
| 482 |
+
"learning_rate": 3.454064729867482e-05,
|
| 483 |
+
"loss": 0.0,
|
| 484 |
+
"step": 6600
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.5367588026149788,
|
| 488 |
+
"grad_norm": 2.717318920986145e-06,
|
| 489 |
+
"learning_rate": 3.422209480122324e-05,
|
| 490 |
+
"loss": 0.0,
|
| 491 |
+
"step": 6700
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.5596972129831403,
|
| 495 |
+
"grad_norm": 1.162458488579432e-06,
|
| 496 |
+
"learning_rate": 3.390354230377166e-05,
|
| 497 |
+
"loss": 0.0,
|
| 498 |
+
"step": 6800
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.5826356233513017,
|
| 502 |
+
"grad_norm": 1.7770501017366769e-06,
|
| 503 |
+
"learning_rate": 3.3584989806320086e-05,
|
| 504 |
+
"loss": 0.0,
|
| 505 |
+
"step": 6900
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.6055740337194633,
|
| 509 |
+
"grad_norm": 1.4451183005803614e-06,
|
| 510 |
+
"learning_rate": 3.32664373088685e-05,
|
| 511 |
+
"loss": 0.0,
|
| 512 |
+
"step": 7000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.6285124440876246,
|
| 516 |
+
"grad_norm": 3.033783741557272e-06,
|
| 517 |
+
"learning_rate": 3.2947884811416926e-05,
|
| 518 |
+
"loss": 0.0,
|
| 519 |
+
"step": 7100
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.6514508544557862,
|
| 523 |
+
"grad_norm": 1.1340368928358657e-06,
|
| 524 |
+
"learning_rate": 3.262933231396534e-05,
|
| 525 |
+
"loss": 0.0,
|
| 526 |
+
"step": 7200
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.6743892648239478,
|
| 530 |
+
"grad_norm": 1.2689773711827002e-06,
|
| 531 |
+
"learning_rate": 3.2310779816513766e-05,
|
| 532 |
+
"loss": 0.0,
|
| 533 |
+
"step": 7300
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.6973276751921091,
|
| 537 |
+
"grad_norm": 2.7127709927299293e-06,
|
| 538 |
+
"learning_rate": 3.199222731906218e-05,
|
| 539 |
+
"loss": 0.0,
|
| 540 |
+
"step": 7400
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.7202660855602707,
|
| 544 |
+
"grad_norm": 1.0890358908000053e-06,
|
| 545 |
+
"learning_rate": 3.1673674821610605e-05,
|
| 546 |
+
"loss": 0.0,
|
| 547 |
+
"step": 7500
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.743204495928432,
|
| 551 |
+
"grad_norm": 1.0123217180080246e-06,
|
| 552 |
+
"learning_rate": 3.135512232415902e-05,
|
| 553 |
+
"loss": 0.0,
|
| 554 |
+
"step": 7600
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.7661429062965937,
|
| 558 |
+
"grad_norm": 1.0123065976586076e-06,
|
| 559 |
+
"learning_rate": 3.1036569826707445e-05,
|
| 560 |
+
"loss": 0.0,
|
| 561 |
+
"step": 7700
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.7890813166647552,
|
| 565 |
+
"grad_norm": 1.1159958148709848e-06,
|
| 566 |
+
"learning_rate": 3.071801732925586e-05,
|
| 567 |
+
"loss": 0.0,
|
| 568 |
+
"step": 7800
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.8120197270329166,
|
| 572 |
+
"grad_norm": 7.618372137585538e-07,
|
| 573 |
+
"learning_rate": 3.039946483180428e-05,
|
| 574 |
+
"loss": 0.0,
|
| 575 |
+
"step": 7900
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.8349581374010782,
|
| 579 |
+
"grad_norm": 1.1276981695118593e-06,
|
| 580 |
+
"learning_rate": 3.00809123343527e-05,
|
| 581 |
+
"loss": 0.0,
|
| 582 |
+
"step": 8000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.8578965477692395,
|
| 586 |
+
"grad_norm": 1.2691349411397823e-06,
|
| 587 |
+
"learning_rate": 2.976235983690112e-05,
|
| 588 |
+
"loss": 0.0,
|
| 589 |
+
"step": 8100
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.880834958137401,
|
| 593 |
+
"grad_norm": 1.1746386689992505e-06,
|
| 594 |
+
"learning_rate": 2.944380733944954e-05,
|
| 595 |
+
"loss": 0.0,
|
| 596 |
+
"step": 8200
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.9037733685055627,
|
| 600 |
+
"grad_norm": 2.057612618955318e-06,
|
| 601 |
+
"learning_rate": 2.912525484199796e-05,
|
| 602 |
+
"loss": 0.0,
|
| 603 |
+
"step": 8300
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.926711778873724,
|
| 607 |
+
"grad_norm": 8.718508865968033e-07,
|
| 608 |
+
"learning_rate": 2.880670234454638e-05,
|
| 609 |
+
"loss": 0.0,
|
| 610 |
+
"step": 8400
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.9496501892418854,
|
| 614 |
+
"grad_norm": 1.6281912849080982e-06,
|
| 615 |
+
"learning_rate": 2.8488149847094804e-05,
|
| 616 |
+
"loss": 0.0,
|
| 617 |
+
"step": 8500
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.972588599610047,
|
| 621 |
+
"grad_norm": 6.946272037566814e-07,
|
| 622 |
+
"learning_rate": 2.8169597349643224e-05,
|
| 623 |
+
"loss": 0.0,
|
| 624 |
+
"step": 8600
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.9955270099782085,
|
| 628 |
+
"grad_norm": 7.4337913247291e-07,
|
| 629 |
+
"learning_rate": 2.7851044852191644e-05,
|
| 630 |
+
"loss": 0.0,
|
| 631 |
+
"step": 8700
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 2.0,
|
| 635 |
+
"eval_accuracy": 1.0,
|
| 636 |
+
"eval_f1": 1.0,
|
| 637 |
+
"eval_loss": 0.0,
|
| 638 |
+
"eval_precision": 1.0,
|
| 639 |
+
"eval_recall": 1.0,
|
| 640 |
+
"eval_runtime": 343.3577,
|
| 641 |
+
"eval_samples_per_second": 50.784,
|
| 642 |
+
"eval_steps_per_second": 3.175,
|
| 643 |
+
"step": 8720
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 2.018350728294529,
|
| 647 |
+
"grad_norm": 2.445955033181235e-06,
|
| 648 |
+
"learning_rate": 2.7532492354740064e-05,
|
| 649 |
+
"loss": 0.0,
|
| 650 |
+
"step": 8800
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.0412891386626906,
|
| 654 |
+
"grad_norm": 8.972128284767678e-07,
|
| 655 |
+
"learning_rate": 2.7213939857288484e-05,
|
| 656 |
+
"loss": 0.0,
|
| 657 |
+
"step": 8900
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.064227549030852,
|
| 661 |
+
"grad_norm": 5.759555961049045e-07,
|
| 662 |
+
"learning_rate": 2.6895387359836904e-05,
|
| 663 |
+
"loss": 0.0,
|
| 664 |
+
"step": 9000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.0871659593990137,
|
| 668 |
+
"grad_norm": 7.570725415462221e-07,
|
| 669 |
+
"learning_rate": 2.6576834862385324e-05,
|
| 670 |
+
"loss": 0.0,
|
| 671 |
+
"step": 9100
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.1101043697671753,
|
| 675 |
+
"grad_norm": 6.959637630643556e-07,
|
| 676 |
+
"learning_rate": 2.6258282364933743e-05,
|
| 677 |
+
"loss": 0.0,
|
| 678 |
+
"step": 9200
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.1330427801353364,
|
| 682 |
+
"grad_norm": 6.756280868103204e-07,
|
| 683 |
+
"learning_rate": 2.593972986748216e-05,
|
| 684 |
+
"loss": 0.0,
|
| 685 |
+
"step": 9300
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.155981190503498,
|
| 689 |
+
"grad_norm": 7.722316581748601e-07,
|
| 690 |
+
"learning_rate": 2.562117737003058e-05,
|
| 691 |
+
"loss": 0.0,
|
| 692 |
+
"step": 9400
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.1789196008716596,
|
| 696 |
+
"grad_norm": 5.774248279521998e-07,
|
| 697 |
+
"learning_rate": 2.5302624872579e-05,
|
| 698 |
+
"loss": 0.0,
|
| 699 |
+
"step": 9500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.201858011239821,
|
| 703 |
+
"grad_norm": 5.61651461339352e-07,
|
| 704 |
+
"learning_rate": 2.498407237512742e-05,
|
| 705 |
+
"loss": 0.0,
|
| 706 |
+
"step": 9600
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.2247964216079827,
|
| 710 |
+
"grad_norm": 3.2662783269188367e-06,
|
| 711 |
+
"learning_rate": 2.466551987767584e-05,
|
| 712 |
+
"loss": 0.0,
|
| 713 |
+
"step": 9700
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.247734831976144,
|
| 717 |
+
"grad_norm": 5.740246820096218e-07,
|
| 718 |
+
"learning_rate": 2.4346967380224263e-05,
|
| 719 |
+
"loss": 0.0,
|
| 720 |
+
"step": 9800
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.2706732423443055,
|
| 724 |
+
"grad_norm": 8.198475143217365e-07,
|
| 725 |
+
"learning_rate": 2.4028414882772683e-05,
|
| 726 |
+
"loss": 0.0,
|
| 727 |
+
"step": 9900
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 2.293611652712467,
|
| 731 |
+
"grad_norm": 5.943483074588585e-07,
|
| 732 |
+
"learning_rate": 2.3709862385321103e-05,
|
| 733 |
+
"loss": 0.0,
|
| 734 |
+
"step": 10000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.3165500630806286,
|
| 738 |
+
"grad_norm": 4.994344067199563e-07,
|
| 739 |
+
"learning_rate": 2.3391309887869522e-05,
|
| 740 |
+
"loss": 0.0,
|
| 741 |
+
"step": 10100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.33948847344879,
|
| 745 |
+
"grad_norm": 5.787817372038262e-07,
|
| 746 |
+
"learning_rate": 2.3072757390417942e-05,
|
| 747 |
+
"loss": 0.0,
|
| 748 |
+
"step": 10200
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.3624268838169513,
|
| 752 |
+
"grad_norm": 6.035662067915837e-07,
|
| 753 |
+
"learning_rate": 2.2754204892966362e-05,
|
| 754 |
+
"loss": 0.0,
|
| 755 |
+
"step": 10300
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.385365294185113,
|
| 759 |
+
"grad_norm": 6.968316483835224e-07,
|
| 760 |
+
"learning_rate": 2.2435652395514782e-05,
|
| 761 |
+
"loss": 0.0,
|
| 762 |
+
"step": 10400
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 2.4083037045532745,
|
| 766 |
+
"grad_norm": 5.578097557190631e-07,
|
| 767 |
+
"learning_rate": 2.2117099898063202e-05,
|
| 768 |
+
"loss": 0.0,
|
| 769 |
+
"step": 10500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.431242114921436,
|
| 773 |
+
"grad_norm": 5.246223508947878e-07,
|
| 774 |
+
"learning_rate": 2.1798547400611622e-05,
|
| 775 |
+
"loss": 0.0,
|
| 776 |
+
"step": 10600
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.4541805252895976,
|
| 780 |
+
"grad_norm": 5.867889285582351e-07,
|
| 781 |
+
"learning_rate": 2.1479994903160042e-05,
|
| 782 |
+
"loss": 0.0,
|
| 783 |
+
"step": 10700
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.4771189356577588,
|
| 787 |
+
"grad_norm": 4.947526122123236e-07,
|
| 788 |
+
"learning_rate": 2.116144240570846e-05,
|
| 789 |
+
"loss": 0.0,
|
| 790 |
+
"step": 10800
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 2.5000573460259203,
|
| 794 |
+
"grad_norm": 7.670053605579596e-07,
|
| 795 |
+
"learning_rate": 2.084288990825688e-05,
|
| 796 |
+
"loss": 0.0,
|
| 797 |
+
"step": 10900
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 2.522995756394082,
|
| 801 |
+
"grad_norm": 6.710503157592029e-07,
|
| 802 |
+
"learning_rate": 2.05243374108053e-05,
|
| 803 |
+
"loss": 0.0,
|
| 804 |
+
"step": 11000
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.5459341667622435,
|
| 808 |
+
"grad_norm": 6.09717119459674e-07,
|
| 809 |
+
"learning_rate": 2.0205784913353725e-05,
|
| 810 |
+
"loss": 0.0,
|
| 811 |
+
"step": 11100
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 2.5688725771304046,
|
| 815 |
+
"grad_norm": 4.0628717101753864e-07,
|
| 816 |
+
"learning_rate": 1.988723241590214e-05,
|
| 817 |
+
"loss": 0.0,
|
| 818 |
+
"step": 11200
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.591810987498566,
|
| 822 |
+
"grad_norm": 5.194257823859516e-07,
|
| 823 |
+
"learning_rate": 1.956867991845056e-05,
|
| 824 |
+
"loss": 0.0,
|
| 825 |
+
"step": 11300
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.6147493978667278,
|
| 829 |
+
"grad_norm": 5.950200261395366e-07,
|
| 830 |
+
"learning_rate": 1.925012742099898e-05,
|
| 831 |
+
"loss": 0.0,
|
| 832 |
+
"step": 11400
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 2.6376878082348894,
|
| 836 |
+
"grad_norm": 5.413147619037773e-07,
|
| 837 |
+
"learning_rate": 1.89315749235474e-05,
|
| 838 |
+
"loss": 0.0,
|
| 839 |
+
"step": 11500
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 2.660626218603051,
|
| 843 |
+
"grad_norm": 4.3072932953691634e-07,
|
| 844 |
+
"learning_rate": 1.861302242609582e-05,
|
| 845 |
+
"loss": 0.0,
|
| 846 |
+
"step": 11600
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 2.6835646289712125,
|
| 850 |
+
"grad_norm": 5.671867597811797e-07,
|
| 851 |
+
"learning_rate": 1.829446992864424e-05,
|
| 852 |
+
"loss": 0.0,
|
| 853 |
+
"step": 11700
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 2.7065030393393736,
|
| 857 |
+
"grad_norm": 4.88942816900817e-07,
|
| 858 |
+
"learning_rate": 1.7979102956167177e-05,
|
| 859 |
+
"loss": 0.0041,
|
| 860 |
+
"step": 11800
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 2.729441449707535,
|
| 864 |
+
"grad_norm": 5.162837055650016e-07,
|
| 865 |
+
"learning_rate": 1.7660550458715597e-05,
|
| 866 |
+
"loss": 0.0,
|
| 867 |
+
"step": 11900
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.752379860075697,
|
| 871 |
+
"grad_norm": 5.953765480626316e-07,
|
| 872 |
+
"learning_rate": 1.7341997961264017e-05,
|
| 873 |
+
"loss": 0.0,
|
| 874 |
+
"step": 12000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.7753182704438584,
|
| 878 |
+
"grad_norm": 2.1004482277930947e-06,
|
| 879 |
+
"learning_rate": 1.7023445463812437e-05,
|
| 880 |
+
"loss": 0.0,
|
| 881 |
+
"step": 12100
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 2.7982566808120195,
|
| 885 |
+
"grad_norm": 4.830233706343279e-07,
|
| 886 |
+
"learning_rate": 1.6704892966360856e-05,
|
| 887 |
+
"loss": 0.0,
|
| 888 |
+
"step": 12200
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 2.821195091180181,
|
| 892 |
+
"grad_norm": 3.652270947895886e-07,
|
| 893 |
+
"learning_rate": 1.638634046890928e-05,
|
| 894 |
+
"loss": 0.0,
|
| 895 |
+
"step": 12300
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 2.8441335015483427,
|
| 899 |
+
"grad_norm": 1.8413612679069047e-06,
|
| 900 |
+
"learning_rate": 1.6067787971457696e-05,
|
| 901 |
+
"loss": 0.0,
|
| 902 |
+
"step": 12400
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 2.8670719119165042,
|
| 906 |
+
"grad_norm": 4.999230327484838e-07,
|
| 907 |
+
"learning_rate": 1.5749235474006116e-05,
|
| 908 |
+
"loss": 0.0,
|
| 909 |
+
"step": 12500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.890010322284666,
|
| 913 |
+
"grad_norm": 5.655538188875653e-07,
|
| 914 |
+
"learning_rate": 1.5430682976554536e-05,
|
| 915 |
+
"loss": 0.0,
|
| 916 |
+
"step": 12600
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 2.9129487326528274,
|
| 920 |
+
"grad_norm": 1.9848837382596685e-06,
|
| 921 |
+
"learning_rate": 1.5112130479102956e-05,
|
| 922 |
+
"loss": 0.0,
|
| 923 |
+
"step": 12700
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 2.9358871430209885,
|
| 927 |
+
"grad_norm": 6.09657490713289e-07,
|
| 928 |
+
"learning_rate": 1.4793577981651377e-05,
|
| 929 |
+
"loss": 0.0,
|
| 930 |
+
"step": 12800
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 2.95882555338915,
|
| 934 |
+
"grad_norm": 5.037222763348836e-07,
|
| 935 |
+
"learning_rate": 1.4475025484199797e-05,
|
| 936 |
+
"loss": 0.0,
|
| 937 |
+
"step": 12900
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 2.9817639637573117,
|
| 941 |
+
"grad_norm": 4.1535062678121903e-07,
|
| 942 |
+
"learning_rate": 1.4156472986748217e-05,
|
| 943 |
+
"loss": 0.0,
|
| 944 |
+
"step": 13000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.0,
|
| 948 |
+
"eval_accuracy": 1.0,
|
| 949 |
+
"eval_f1": 1.0,
|
| 950 |
+
"eval_loss": 0.0,
|
| 951 |
+
"eval_precision": 1.0,
|
| 952 |
+
"eval_recall": 1.0,
|
| 953 |
+
"eval_runtime": 344.2572,
|
| 954 |
+
"eval_samples_per_second": 50.651,
|
| 955 |
+
"eval_steps_per_second": 3.166,
|
| 956 |
+
"step": 13080
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 3.004587682073632,
|
| 960 |
+
"grad_norm": 6.05821981025656e-07,
|
| 961 |
+
"learning_rate": 1.3837920489296639e-05,
|
| 962 |
+
"loss": 0.0,
|
| 963 |
+
"step": 13100
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 3.0275260924417937,
|
| 967 |
+
"grad_norm": 6.071956022424274e-07,
|
| 968 |
+
"learning_rate": 1.3519367991845055e-05,
|
| 969 |
+
"loss": 0.0,
|
| 970 |
+
"step": 13200
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 3.0504645028099553,
|
| 974 |
+
"grad_norm": 1.934891088239965e-06,
|
| 975 |
+
"learning_rate": 1.3200815494393475e-05,
|
| 976 |
+
"loss": 0.0,
|
| 977 |
+
"step": 13300
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.073402913178117,
|
| 981 |
+
"grad_norm": 2.5065089630516013e-06,
|
| 982 |
+
"learning_rate": 1.2882262996941897e-05,
|
| 983 |
+
"loss": 0.0,
|
| 984 |
+
"step": 13400
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 3.0963413235462784,
|
| 988 |
+
"grad_norm": 5.728885753342183e-06,
|
| 989 |
+
"learning_rate": 1.2563710499490317e-05,
|
| 990 |
+
"loss": 0.0,
|
| 991 |
+
"step": 13500
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 3.1192797339144396,
|
| 995 |
+
"grad_norm": 4.320262178225676e-06,
|
| 996 |
+
"learning_rate": 1.2245158002038737e-05,
|
| 997 |
+
"loss": 0.0,
|
| 998 |
+
"step": 13600
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.142218144282601,
|
| 1002 |
+
"grad_norm": 4.542172007404588e-07,
|
| 1003 |
+
"learning_rate": 1.1926605504587156e-05,
|
| 1004 |
+
"loss": 0.0,
|
| 1005 |
+
"step": 13700
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 3.1651565546507627,
|
| 1009 |
+
"grad_norm": 3.681015243728325e-07,
|
| 1010 |
+
"learning_rate": 1.1608053007135576e-05,
|
| 1011 |
+
"loss": 0.0,
|
| 1012 |
+
"step": 13800
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 3.1880949650189243,
|
| 1016 |
+
"grad_norm": 4.951008918396838e-07,
|
| 1017 |
+
"learning_rate": 1.1289500509683996e-05,
|
| 1018 |
+
"loss": 0.0,
|
| 1019 |
+
"step": 13900
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 3.2110333753870854,
|
| 1023 |
+
"grad_norm": 4.484388966830011e-07,
|
| 1024 |
+
"learning_rate": 1.0970948012232416e-05,
|
| 1025 |
+
"loss": 0.0,
|
| 1026 |
+
"step": 14000
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 3.233971785755247,
|
| 1030 |
+
"grad_norm": 5.063902790425345e-07,
|
| 1031 |
+
"learning_rate": 1.0652395514780836e-05,
|
| 1032 |
+
"loss": 0.0,
|
| 1033 |
+
"step": 14100
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 3.2569101961234086,
|
| 1037 |
+
"grad_norm": 4.447717003586149e-07,
|
| 1038 |
+
"learning_rate": 1.0333843017329256e-05,
|
| 1039 |
+
"loss": 0.0,
|
| 1040 |
+
"step": 14200
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.27984860649157,
|
| 1044 |
+
"grad_norm": 7.843581215638551e-07,
|
| 1045 |
+
"learning_rate": 1.0015290519877676e-05,
|
| 1046 |
+
"loss": 0.0,
|
| 1047 |
+
"step": 14300
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 3.3027870168597318,
|
| 1051 |
+
"grad_norm": 4.5617230171046685e-07,
|
| 1052 |
+
"learning_rate": 9.696738022426097e-06,
|
| 1053 |
+
"loss": 0.0,
|
| 1054 |
+
"step": 14400
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 3.3257254272278933,
|
| 1058 |
+
"grad_norm": 3.457494130998384e-07,
|
| 1059 |
+
"learning_rate": 9.378185524974515e-06,
|
| 1060 |
+
"loss": 0.0,
|
| 1061 |
+
"step": 14500
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 3.3486638375960545,
|
| 1065 |
+
"grad_norm": 4.5762243416902493e-07,
|
| 1066 |
+
"learning_rate": 9.059633027522935e-06,
|
| 1067 |
+
"loss": 0.0,
|
| 1068 |
+
"step": 14600
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 3.371602247964216,
|
| 1072 |
+
"grad_norm": 5.967251013316854e-07,
|
| 1073 |
+
"learning_rate": 8.741080530071357e-06,
|
| 1074 |
+
"loss": 0.0,
|
| 1075 |
+
"step": 14700
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 3.3945406583323776,
|
| 1079 |
+
"grad_norm": 3.912183217380516e-07,
|
| 1080 |
+
"learning_rate": 8.422528032619777e-06,
|
| 1081 |
+
"loss": 0.0,
|
| 1082 |
+
"step": 14800
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 3.417479068700539,
|
| 1086 |
+
"grad_norm": 2.0574229893099982e-06,
|
| 1087 |
+
"learning_rate": 8.103975535168195e-06,
|
| 1088 |
+
"loss": 0.0,
|
| 1089 |
+
"step": 14900
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 3.4404174790687003,
|
| 1093 |
+
"grad_norm": 5.268063887342578e-06,
|
| 1094 |
+
"learning_rate": 7.785423037716617e-06,
|
| 1095 |
+
"loss": 0.0,
|
| 1096 |
+
"step": 15000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 3.463355889436862,
|
| 1100 |
+
"grad_norm": 4.4349508243612945e-07,
|
| 1101 |
+
"learning_rate": 7.4668705402650365e-06,
|
| 1102 |
+
"loss": 0.0,
|
| 1103 |
+
"step": 15100
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 3.4862942998050235,
|
| 1107 |
+
"grad_norm": 3.2844191082403995e-06,
|
| 1108 |
+
"learning_rate": 7.148318042813456e-06,
|
| 1109 |
+
"loss": 0.0,
|
| 1110 |
+
"step": 15200
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 3.509232710173185,
|
| 1114 |
+
"grad_norm": 6.628841902056593e-07,
|
| 1115 |
+
"learning_rate": 6.8297655453618754e-06,
|
| 1116 |
+
"loss": 0.0,
|
| 1117 |
+
"step": 15300
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 3.5321711205413466,
|
| 1121 |
+
"grad_norm": 4.5607134779857006e-07,
|
| 1122 |
+
"learning_rate": 6.511213047910296e-06,
|
| 1123 |
+
"loss": 0.0,
|
| 1124 |
+
"step": 15400
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 3.555109530909508,
|
| 1128 |
+
"grad_norm": 5.205767479310452e-07,
|
| 1129 |
+
"learning_rate": 6.192660550458716e-06,
|
| 1130 |
+
"loss": 0.0,
|
| 1131 |
+
"step": 15500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 3.5780479412776693,
|
| 1135 |
+
"grad_norm": 5.164214940123202e-07,
|
| 1136 |
+
"learning_rate": 5.874108053007136e-06,
|
| 1137 |
+
"loss": 0.0,
|
| 1138 |
+
"step": 15600
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 3.600986351645831,
|
| 1142 |
+
"grad_norm": 4.506584048158402e-07,
|
| 1143 |
+
"learning_rate": 5.558741080530071e-06,
|
| 1144 |
+
"loss": 0.0076,
|
| 1145 |
+
"step": 15700
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 3.6239247620139925,
|
| 1149 |
+
"grad_norm": 6.092589615036559e-07,
|
| 1150 |
+
"learning_rate": 5.240188583078492e-06,
|
| 1151 |
+
"loss": 0.0,
|
| 1152 |
+
"step": 15800
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 3.646863172382154,
|
| 1156 |
+
"grad_norm": 4.135415110795293e-06,
|
| 1157 |
+
"learning_rate": 4.921636085626911e-06,
|
| 1158 |
+
"loss": 0.0,
|
| 1159 |
+
"step": 15900
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 3.669801582750315,
|
| 1163 |
+
"grad_norm": 6.201661335580866e-07,
|
| 1164 |
+
"learning_rate": 4.603083588175332e-06,
|
| 1165 |
+
"loss": 0.0,
|
| 1166 |
+
"step": 16000
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 3.692739993118477,
|
| 1170 |
+
"grad_norm": 6.843212077001226e-07,
|
| 1171 |
+
"learning_rate": 4.284531090723752e-06,
|
| 1172 |
+
"loss": 0.0,
|
| 1173 |
+
"step": 16100
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 3.7156784034866384,
|
| 1177 |
+
"grad_norm": 6.781843921999098e-07,
|
| 1178 |
+
"learning_rate": 3.9659785932721716e-06,
|
| 1179 |
+
"loss": 0.0,
|
| 1180 |
+
"step": 16200
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 3.7386168138548,
|
| 1184 |
+
"grad_norm": 5.762826731370296e-07,
|
| 1185 |
+
"learning_rate": 3.6474260958205915e-06,
|
| 1186 |
+
"loss": 0.0,
|
| 1187 |
+
"step": 16300
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 3.7615552242229615,
|
| 1191 |
+
"grad_norm": 5.510862592927879e-07,
|
| 1192 |
+
"learning_rate": 3.3288735983690118e-06,
|
| 1193 |
+
"loss": 0.0,
|
| 1194 |
+
"step": 16400
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 3.784493634591123,
|
| 1198 |
+
"grad_norm": 6.336876481327636e-07,
|
| 1199 |
+
"learning_rate": 3.0103211009174312e-06,
|
| 1200 |
+
"loss": 0.0,
|
| 1201 |
+
"step": 16500
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 3.8074320449592842,
|
| 1205 |
+
"grad_norm": 4.1163076502925833e-07,
|
| 1206 |
+
"learning_rate": 2.691768603465851e-06,
|
| 1207 |
+
"loss": 0.0,
|
| 1208 |
+
"step": 16600
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 3.830370455327446,
|
| 1212 |
+
"grad_norm": 5.610125981547753e-07,
|
| 1213 |
+
"learning_rate": 2.3732161060142714e-06,
|
| 1214 |
+
"loss": 0.0,
|
| 1215 |
+
"step": 16700
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 3.8533088656956074,
|
| 1219 |
+
"grad_norm": 5.504385853782878e-07,
|
| 1220 |
+
"learning_rate": 2.0546636085626913e-06,
|
| 1221 |
+
"loss": 0.0,
|
| 1222 |
+
"step": 16800
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 3.8762472760637685,
|
| 1226 |
+
"grad_norm": 5.19926686592953e-07,
|
| 1227 |
+
"learning_rate": 1.7361111111111112e-06,
|
| 1228 |
+
"loss": 0.0,
|
| 1229 |
+
"step": 16900
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 3.89918568643193,
|
| 1233 |
+
"grad_norm": 6.166213779579266e-07,
|
| 1234 |
+
"learning_rate": 1.417558613659531e-06,
|
| 1235 |
+
"loss": 0.0,
|
| 1236 |
+
"step": 17000
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 3.9221240968000917,
|
| 1240 |
+
"grad_norm": 5.947557042418339e-07,
|
| 1241 |
+
"learning_rate": 1.099006116207951e-06,
|
| 1242 |
+
"loss": 0.0,
|
| 1243 |
+
"step": 17100
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 3.9450625071682532,
|
| 1247 |
+
"grad_norm": 5.760847443525563e-07,
|
| 1248 |
+
"learning_rate": 7.804536187563711e-07,
|
| 1249 |
+
"loss": 0.0,
|
| 1250 |
+
"step": 17200
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 3.968000917536415,
|
| 1254 |
+
"grad_norm": 1.4817189821769716e-06,
|
| 1255 |
+
"learning_rate": 4.6190112130479106e-07,
|
| 1256 |
+
"loss": 0.0,
|
| 1257 |
+
"step": 17300
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 3.9909393279045764,
|
| 1261 |
+
"grad_norm": 4.664090056394343e-07,
|
| 1262 |
+
"learning_rate": 1.4334862385321102e-07,
|
| 1263 |
+
"loss": 0.0,
|
| 1264 |
+
"step": 17400
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 4.0,
|
| 1268 |
+
"eval_accuracy": 1.0,
|
| 1269 |
+
"eval_f1": 1.0,
|
| 1270 |
+
"eval_loss": 0.0,
|
| 1271 |
+
"eval_precision": 1.0,
|
| 1272 |
+
"eval_recall": 1.0,
|
| 1273 |
+
"eval_runtime": 344.4309,
|
| 1274 |
+
"eval_samples_per_second": 50.626,
|
| 1275 |
+
"eval_steps_per_second": 3.165,
|
| 1276 |
+
"step": 17440
|
| 1277 |
+
}
|
| 1278 |
+
],
|
| 1279 |
+
"logging_steps": 100,
|
| 1280 |
+
"max_steps": 17440,
|
| 1281 |
+
"num_input_tokens_seen": 0,
|
| 1282 |
+
"num_train_epochs": 4,
|
| 1283 |
+
"save_steps": 500,
|
| 1284 |
+
"stateful_callbacks": {
|
| 1285 |
+
"TrainerControl": {
|
| 1286 |
+
"args": {
|
| 1287 |
+
"should_epoch_stop": false,
|
| 1288 |
+
"should_evaluate": false,
|
| 1289 |
+
"should_log": false,
|
| 1290 |
+
"should_save": true,
|
| 1291 |
+
"should_training_stop": true
|
| 1292 |
+
},
|
| 1293 |
+
"attributes": {}
|
| 1294 |
+
}
|
| 1295 |
+
},
|
| 1296 |
+
"total_flos": 0.0,
|
| 1297 |
+
"train_batch_size": 16,
|
| 1298 |
+
"trial_name": null,
|
| 1299 |
+
"trial_params": null
|
| 1300 |
+
}
|
checkpoint-17440/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f8ff7fce9461452d8aa4b6184269d8ec95767c5b9ae6ba31d2710345aa0d28b
|
| 3 |
+
size 5777
|
checkpoint-17440/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4360/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4360/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48db7f63f05e60d084aeaea195adc0e7f0bec5f0400c6d46061d6789e6d9410e
|
| 3 |
+
size 498612808
|
checkpoint-4360/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1442006ad7f694ff5ec98e80f180529bd08a18ac90a8626d54566885f0e6b874
|
| 3 |
+
size 992619531
|
checkpoint-4360/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:610b265fa7c86b54e274ddef09bf0bbb06ca3fccf378238dc159d4b1ccbb0d83
|
| 3 |
+
size 14645
|
checkpoint-4360/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53cc2b43bea4cc9438adfeee9c6a91e7bc5a43a417773ac1174cf3143b1a4325
|
| 3 |
+
size 1383
|
checkpoint-4360/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa89540b214736341a069804abeb83194bd13ff406b0f27af90621ec3fe3653c
|
| 3 |
+
size 1465
|
checkpoint-4360/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-4360/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4360/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-4360/trainer_state.json
ADDED
|
@@ -0,0 +1,347 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 4360,
|
| 3 |
+
"best_metric": 1.0,
|
| 4 |
+
"best_model_checkpoint": "gcbert_ckpt/checkpoint-4360",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4360,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.022938410368161487,
|
| 14 |
+
"grad_norm": 29.002798080444336,
|
| 15 |
+
"learning_rate": 2.809633027522936e-06,
|
| 16 |
+
"loss": 1.1878,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.045876820736322974,
|
| 21 |
+
"grad_norm": 68.14753723144531,
|
| 22 |
+
"learning_rate": 5.676605504587156e-06,
|
| 23 |
+
"loss": 0.6556,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06881523110448445,
|
| 28 |
+
"grad_norm": 54.466773986816406,
|
| 29 |
+
"learning_rate": 8.543577981651376e-06,
|
| 30 |
+
"loss": 0.288,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09175364147264595,
|
| 35 |
+
"grad_norm": 0.0029387406539171934,
|
| 36 |
+
"learning_rate": 1.1410550458715597e-05,
|
| 37 |
+
"loss": 0.0993,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11469205184080743,
|
| 42 |
+
"grad_norm": 0.00012727684224955738,
|
| 43 |
+
"learning_rate": 1.4277522935779817e-05,
|
| 44 |
+
"loss": 0.0,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1376304622089689,
|
| 49 |
+
"grad_norm": 0.0007764559122733772,
|
| 50 |
+
"learning_rate": 1.714449541284404e-05,
|
| 51 |
+
"loss": 0.0,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1605688725771304,
|
| 56 |
+
"grad_norm": 7.87975950515829e-05,
|
| 57 |
+
"learning_rate": 2.0011467889908257e-05,
|
| 58 |
+
"loss": 0.0,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1835072829452919,
|
| 63 |
+
"grad_norm": 0.0004955148906446993,
|
| 64 |
+
"learning_rate": 2.2878440366972478e-05,
|
| 65 |
+
"loss": 0.0,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2064456933134534,
|
| 70 |
+
"grad_norm": 0.00011743771756300703,
|
| 71 |
+
"learning_rate": 2.57454128440367e-05,
|
| 72 |
+
"loss": 0.0,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.22938410368161485,
|
| 77 |
+
"grad_norm": 0.0005010354216210544,
|
| 78 |
+
"learning_rate": 2.861238532110092e-05,
|
| 79 |
+
"loss": 0.0,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.25232251404977635,
|
| 84 |
+
"grad_norm": 0.00021343142725527287,
|
| 85 |
+
"learning_rate": 3.147935779816514e-05,
|
| 86 |
+
"loss": 0.0,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.2752609244179378,
|
| 91 |
+
"grad_norm": 0.00011905051360372454,
|
| 92 |
+
"learning_rate": 3.434633027522936e-05,
|
| 93 |
+
"loss": 0.0,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.29819933478609933,
|
| 98 |
+
"grad_norm": 0.00038216536631807685,
|
| 99 |
+
"learning_rate": 3.7213302752293576e-05,
|
| 100 |
+
"loss": 0.0,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3211377451542608,
|
| 105 |
+
"grad_norm": 4.422829078976065e-05,
|
| 106 |
+
"learning_rate": 4.00802752293578e-05,
|
| 107 |
+
"loss": 0.0,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3440761555224223,
|
| 112 |
+
"grad_norm": 0.0002208059886470437,
|
| 113 |
+
"learning_rate": 4.2947247706422025e-05,
|
| 114 |
+
"loss": 0.0,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.3670145658905838,
|
| 119 |
+
"grad_norm": 5.1115232054144144e-05,
|
| 120 |
+
"learning_rate": 4.581422018348624e-05,
|
| 121 |
+
"loss": 0.0,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.38995297625874525,
|
| 126 |
+
"grad_norm": 7.042491051834077e-05,
|
| 127 |
+
"learning_rate": 4.868119266055046e-05,
|
| 128 |
+
"loss": 0.0,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4128913866269068,
|
| 133 |
+
"grad_norm": 3.786469824262895e-05,
|
| 134 |
+
"learning_rate": 4.982798165137615e-05,
|
| 135 |
+
"loss": 0.0,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.43582979699506824,
|
| 140 |
+
"grad_norm": 1.468727168685291e-05,
|
| 141 |
+
"learning_rate": 4.950942915392457e-05,
|
| 142 |
+
"loss": 0.0,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4587682073632297,
|
| 147 |
+
"grad_norm": 3.0084795071161352e-05,
|
| 148 |
+
"learning_rate": 4.919087665647299e-05,
|
| 149 |
+
"loss": 0.0,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.48170661773139123,
|
| 154 |
+
"grad_norm": 2.5331471988465637e-05,
|
| 155 |
+
"learning_rate": 4.887232415902141e-05,
|
| 156 |
+
"loss": 0.0,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.5046450280995527,
|
| 161 |
+
"grad_norm": 2.618041617097333e-05,
|
| 162 |
+
"learning_rate": 4.855377166156983e-05,
|
| 163 |
+
"loss": 0.0,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5275834384677142,
|
| 168 |
+
"grad_norm": 2.4747334464336745e-05,
|
| 169 |
+
"learning_rate": 4.823521916411825e-05,
|
| 170 |
+
"loss": 0.0,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.5505218488358756,
|
| 175 |
+
"grad_norm": 1.4968503819545731e-05,
|
| 176 |
+
"learning_rate": 4.791666666666667e-05,
|
| 177 |
+
"loss": 0.0,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5734602592040372,
|
| 182 |
+
"grad_norm": 0.00038964845589362085,
|
| 183 |
+
"learning_rate": 4.759811416921509e-05,
|
| 184 |
+
"loss": 0.0,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5963986695721987,
|
| 189 |
+
"grad_norm": 2.8935370210092515e-05,
|
| 190 |
+
"learning_rate": 4.7279561671763515e-05,
|
| 191 |
+
"loss": 0.0,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6193370799403601,
|
| 196 |
+
"grad_norm": 8.388165042561013e-06,
|
| 197 |
+
"learning_rate": 4.6961009174311924e-05,
|
| 198 |
+
"loss": 0.0,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.6422754903085216,
|
| 203 |
+
"grad_norm": 1.768140464264434e-05,
|
| 204 |
+
"learning_rate": 4.664245667686035e-05,
|
| 205 |
+
"loss": 0.0,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6652139006766831,
|
| 210 |
+
"grad_norm": 1.36974013003055e-05,
|
| 211 |
+
"learning_rate": 4.6323904179408764e-05,
|
| 212 |
+
"loss": 0.0,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6881523110448446,
|
| 217 |
+
"grad_norm": 9.414131454832386e-06,
|
| 218 |
+
"learning_rate": 4.600535168195719e-05,
|
| 219 |
+
"loss": 0.0,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.7110907214130061,
|
| 224 |
+
"grad_norm": 4.622045162250288e-05,
|
| 225 |
+
"learning_rate": 4.568679918450561e-05,
|
| 226 |
+
"loss": 0.0,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.7340291317811676,
|
| 231 |
+
"grad_norm": 2.692650923563633e-05,
|
| 232 |
+
"learning_rate": 4.536824668705403e-05,
|
| 233 |
+
"loss": 0.0,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.756967542149329,
|
| 238 |
+
"grad_norm": 1.0936350008705631e-05,
|
| 239 |
+
"learning_rate": 4.504969418960245e-05,
|
| 240 |
+
"loss": 0.0,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.7799059525174905,
|
| 245 |
+
"grad_norm": 5.966558546788292e-06,
|
| 246 |
+
"learning_rate": 4.473114169215087e-05,
|
| 247 |
+
"loss": 0.0,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.802844362885652,
|
| 252 |
+
"grad_norm": 9.507278264209162e-06,
|
| 253 |
+
"learning_rate": 4.441258919469929e-05,
|
| 254 |
+
"loss": 0.0,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.8257827732538136,
|
| 259 |
+
"grad_norm": 1.0006630873249378e-05,
|
| 260 |
+
"learning_rate": 4.409403669724771e-05,
|
| 261 |
+
"loss": 0.0,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.848721183621975,
|
| 266 |
+
"grad_norm": 5.595240509137511e-06,
|
| 267 |
+
"learning_rate": 4.377548419979613e-05,
|
| 268 |
+
"loss": 0.0,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.8716595939901365,
|
| 273 |
+
"grad_norm": 8.78509945323458e-06,
|
| 274 |
+
"learning_rate": 4.3456931702344547e-05,
|
| 275 |
+
"loss": 0.0,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.894598004358298,
|
| 280 |
+
"grad_norm": 1.4489376553683542e-05,
|
| 281 |
+
"learning_rate": 4.313837920489297e-05,
|
| 282 |
+
"loss": 0.0,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.9175364147264594,
|
| 287 |
+
"grad_norm": 0.0006358507671393454,
|
| 288 |
+
"learning_rate": 4.281982670744139e-05,
|
| 289 |
+
"loss": 0.0,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.940474825094621,
|
| 294 |
+
"grad_norm": 2.2141068257042207e-05,
|
| 295 |
+
"learning_rate": 4.250127420998981e-05,
|
| 296 |
+
"loss": 0.0,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.9634132354627825,
|
| 301 |
+
"grad_norm": 2.3798056645318866e-06,
|
| 302 |
+
"learning_rate": 4.2182721712538226e-05,
|
| 303 |
+
"loss": 0.0,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9863516458309439,
|
| 308 |
+
"grad_norm": 2.4955927074188367e-05,
|
| 309 |
+
"learning_rate": 4.186416921508665e-05,
|
| 310 |
+
"loss": 0.0,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0,
|
| 315 |
+
"eval_accuracy": 1.0,
|
| 316 |
+
"eval_f1": 1.0,
|
| 317 |
+
"eval_loss": 3.4182854463660206e-11,
|
| 318 |
+
"eval_precision": 1.0,
|
| 319 |
+
"eval_recall": 1.0,
|
| 320 |
+
"eval_runtime": 342.7946,
|
| 321 |
+
"eval_samples_per_second": 50.867,
|
| 322 |
+
"eval_steps_per_second": 3.18,
|
| 323 |
+
"step": 4360
|
| 324 |
+
}
|
| 325 |
+
],
|
| 326 |
+
"logging_steps": 100,
|
| 327 |
+
"max_steps": 17440,
|
| 328 |
+
"num_input_tokens_seen": 0,
|
| 329 |
+
"num_train_epochs": 4,
|
| 330 |
+
"save_steps": 500,
|
| 331 |
+
"stateful_callbacks": {
|
| 332 |
+
"TrainerControl": {
|
| 333 |
+
"args": {
|
| 334 |
+
"should_epoch_stop": false,
|
| 335 |
+
"should_evaluate": false,
|
| 336 |
+
"should_log": false,
|
| 337 |
+
"should_save": true,
|
| 338 |
+
"should_training_stop": false
|
| 339 |
+
},
|
| 340 |
+
"attributes": {}
|
| 341 |
+
}
|
| 342 |
+
},
|
| 343 |
+
"total_flos": 0.0,
|
| 344 |
+
"train_batch_size": 16,
|
| 345 |
+
"trial_name": null,
|
| 346 |
+
"trial_params": null
|
| 347 |
+
}
|
checkpoint-4360/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f8ff7fce9461452d8aa4b6184269d8ec95767c5b9ae6ba31d2710345aa0d28b
|
| 3 |
+
size 5777
|
checkpoint-4360/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_metrics.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_loss": 3.4182854463660206e-11,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_precision": 1.0,
|
| 5 |
+
"eval_recall": 1.0,
|
| 6 |
+
"eval_f1": 1.0,
|
| 7 |
+
"eval_runtime": 343.6441,
|
| 8 |
+
"eval_samples_per_second": 50.741,
|
| 9 |
+
"eval_steps_per_second": 3.172,
|
| 10 |
+
"epoch": 4.0
|
| 11 |
+
}
|
runs/Jul26_05-00-38_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753506039.ip-172-31-31-181.ap-northeast-2.compute.internal.3768.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bd879128a72f712f938e8048c8ab3abb7a5ae8904e572a7b57e3a763eaba285
|
| 3 |
+
size 4263
|
runs/Jul26_05-06-05_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753506367.ip-172-31-31-181.ap-northeast-2.compute.internal.3930.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeca117cbfb72200bcd01e3f32115d0f72416330938612d3c61e6f5933607201
|
| 3 |
+
size 4263
|
runs/Jul26_05-10-49_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753506650.ip-172-31-31-181.ap-northeast-2.compute.internal.4146.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07bcc11a7fae1000e84413eb7c90a25adaa72b1ed4f99024dcade845e2bc4eb8
|
| 3 |
+
size 4470
|
runs/Jul26_05-43-11_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753508592.ip-172-31-31-181.ap-northeast-2.compute.internal.3507.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48ef74a9b78d12b01bbf1162ebe6afba6536fd0adb61761ca205512c4b9f939b
|
| 3 |
+
size 4263
|
runs/Jul26_05-45-04_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753508706.ip-172-31-31-181.ap-northeast-2.compute.internal.3608.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:723cf94095ded58a63acc114879976f60e188b573a370f7310e329372448e5fd
|
| 3 |
+
size 4263
|
runs/Jul26_05-47-54_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753508876.ip-172-31-31-181.ap-northeast-2.compute.internal.3707.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:284b79ec9027fa37232b3d9b40df881e23843a20adf70a0a7e0890193c441833
|
| 3 |
+
size 4470
|
runs/Jul26_05-54-27_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753509268.ip-172-31-31-181.ap-northeast-2.compute.internal.3990.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3081c21b37a2824b19fbf16e045568c39b80fe3b73f8580aadc1e8a1bc6dacc8
|
| 3 |
+
size 4263
|
runs/Jul26_05-56-42_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753509403.ip-172-31-31-181.ap-northeast-2.compute.internal.4124.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd648cb7bee4ca1afbcceb6752883ea025b4c59b2e0811749a9308269a5dde3e
|
| 3 |
+
size 43274
|
runs/Jul26_05-56-42_ip-172-31-31-181.ap-northeast-2.compute.internal/events.out.tfevents.1753534536.ip-172-31-31-181.ap-northeast-2.compute.internal.4124.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ace4c749f3f2927e8cc621c68b15dd2472df687951907d7ad171fc32867b5b37
|
| 3 |
+
size 569
|