taguser commited on
Commit
957496b
·
verified ·
1 Parent(s): 3982c49

Add files using upload-large-folder tool

Browse files
adapter_config.json CHANGED
@@ -24,13 +24,13 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "k_proj",
28
  "q_proj",
29
- "gate_proj",
30
  "v_proj",
31
- "down_proj",
32
- "o_proj",
33
- "up_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "down_proj",
28
  "q_proj",
29
+ "up_proj",
30
  "v_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "o_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6982dd52890652339983132e7b3ce46e4228949dc67b7c326b427c710edb6467
3
  size 275341720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de11d9ee1d9b431c3aa3535a222ac8edd0e90ab134349637a967b7538e0d434
3
  size 275341720
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.6956521739130435,
3
  "total_flos": 3.2641218873655296e+16,
4
- "train_loss": 0.6446424722671509,
5
- "train_runtime": 167.1103,
6
- "train_samples_per_second": 1.652,
7
- "train_steps_per_second": 0.036
8
  }
 
1
  {
2
  "epoch": 2.6956521739130435,
3
  "total_flos": 3.2641218873655296e+16,
4
+ "train_loss": 0.6446646948655447,
5
+ "train_runtime": 174.9578,
6
+ "train_samples_per_second": 1.578,
7
+ "train_steps_per_second": 0.034
8
  }
checkpoint-2/adapter_config.json CHANGED
@@ -24,13 +24,13 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "k_proj",
28
  "q_proj",
29
- "gate_proj",
30
  "v_proj",
31
- "down_proj",
32
- "o_proj",
33
- "up_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "down_proj",
28
  "q_proj",
29
+ "up_proj",
30
  "v_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "o_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
checkpoint-2/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d2370b0743a35720f4698120b02afa5ad04d620a283b0fdb5327534b84d7ea0
3
  size 275341720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05202bbc525e4f36902da388c48123de91bf4ab4f9ea8f310e8deab7370ad5e5
3
  size 275341720
checkpoint-2/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7319d061628852e11c77fadad09c4a99ae679af7ee300e9023ff1f39d6f105f5
3
  size 551070979
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b33675fe214b73f1979c296fcd1c4d35567bc753b7d743897ce2f61d8d712e0c
3
  size 551070979
checkpoint-2/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2072c2a3d329371b4bb7e84363ffd001c562e727dc7072c974ab01eb54c91cf0
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a766645fa638fefb39182a9a3c4dff0218f23b6ac8611b7b646c151662ea97
3
  size 6097
checkpoint-4/adapter_config.json CHANGED
@@ -24,13 +24,13 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "k_proj",
28
  "q_proj",
29
- "gate_proj",
30
  "v_proj",
31
- "down_proj",
32
- "o_proj",
33
- "up_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "down_proj",
28
  "q_proj",
29
+ "up_proj",
30
  "v_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "o_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
checkpoint-4/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c71d52e60f7b288368cb8efa38fe1483fc5d17dc5898d4bd5102759675b607d4
3
  size 275341720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69436d90a28f3dbe26a7ab1939b9a78a03422bda96bdc67f7a22a4095bbe99ac
3
  size 275341720
checkpoint-4/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ad013bafb31455033ad0c3f118e469d559871379fe1447561b33f60b6ecbf74
3
  size 551070979
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcfac64fa2fb220be7395190b245267f7c86b228f69ddfd5a99e9bd776a4a76e
3
  size 551070979
checkpoint-4/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2072c2a3d329371b4bb7e84363ffd001c562e727dc7072c974ab01eb54c91cf0
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a766645fa638fefb39182a9a3c4dff0218f23b6ac8611b7b646c151662ea97
3
  size 6097
checkpoint-6/adapter_config.json CHANGED
@@ -24,13 +24,13 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "k_proj",
28
  "q_proj",
29
- "gate_proj",
30
  "v_proj",
31
- "down_proj",
32
- "o_proj",
33
- "up_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
+ "down_proj",
28
  "q_proj",
29
+ "up_proj",
30
  "v_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "o_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
checkpoint-6/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6982dd52890652339983132e7b3ce46e4228949dc67b7c326b427c710edb6467
3
  size 275341720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7de11d9ee1d9b431c3aa3535a222ac8edd0e90ab134349637a967b7538e0d434
3
  size 275341720
checkpoint-6/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b678ce4dd6d4acfafb7b36bbde95aef0183567adb63941f7e917146c77a52549
3
  size 551070979
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f077c99abc31de70448062a0bb93ffd884add53edba2b82c4bb29f5f8d6edbd9
3
  size 551070979
checkpoint-6/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 2.3478260869565215,
14
- "grad_norm": 0.06545385718345642,
15
  "learning_rate": 1.7274575140626318e-05,
16
  "loss": 0.6796,
17
  "step": 5
 
11
  "log_history": [
12
  {
13
  "epoch": 2.3478260869565215,
14
+ "grad_norm": 0.0659269466996193,
15
  "learning_rate": 1.7274575140626318e-05,
16
  "loss": 0.6796,
17
  "step": 5
checkpoint-6/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2072c2a3d329371b4bb7e84363ffd001c562e727dc7072c974ab01eb54c91cf0
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a766645fa638fefb39182a9a3c4dff0218f23b6ac8611b7b646c151662ea97
3
  size 6097
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.6956521739130435,
3
  "total_flos": 3.2641218873655296e+16,
4
- "train_loss": 0.6446424722671509,
5
- "train_runtime": 167.1103,
6
- "train_samples_per_second": 1.652,
7
- "train_steps_per_second": 0.036
8
  }
 
1
  {
2
  "epoch": 2.6956521739130435,
3
  "total_flos": 3.2641218873655296e+16,
4
+ "train_loss": 0.6446646948655447,
5
+ "train_runtime": 174.9578,
6
+ "train_samples_per_second": 1.578,
7
+ "train_steps_per_second": 0.034
8
  }
trainer_log.jsonl CHANGED
@@ -1,2 +1,2 @@
1
- {"current_steps": 5, "total_steps": 6, "loss": 0.6796, "lr": 1.7274575140626318e-05, "epoch": 2.3478260869565215, "percentage": 83.33, "elapsed_time": "0:02:19", "remaining_time": "0:00:27"}
2
- {"current_steps": 6, "total_steps": 6, "epoch": 2.6956521739130435, "percentage": 100.0, "elapsed_time": "0:02:44", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 5, "total_steps": 6, "loss": 0.6796, "lr": 1.7274575140626318e-05, "epoch": 2.3478260869565215, "percentage": 83.33, "elapsed_time": "0:02:28", "remaining_time": "0:00:29"}
2
+ {"current_steps": 6, "total_steps": 6, "epoch": 2.6956521739130435, "percentage": 100.0, "elapsed_time": "0:02:52", "remaining_time": "0:00:00"}
trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 2.3478260869565215,
14
- "grad_norm": 0.06545385718345642,
15
  "learning_rate": 1.7274575140626318e-05,
16
  "loss": 0.6796,
17
  "step": 5
@@ -20,10 +20,10 @@
20
  "epoch": 2.6956521739130435,
21
  "step": 6,
22
  "total_flos": 3.2641218873655296e+16,
23
- "train_loss": 0.6446424722671509,
24
- "train_runtime": 167.1103,
25
- "train_samples_per_second": 1.652,
26
- "train_steps_per_second": 0.036
27
  }
28
  ],
29
  "logging_steps": 5,
 
11
  "log_history": [
12
  {
13
  "epoch": 2.3478260869565215,
14
+ "grad_norm": 0.0659269466996193,
15
  "learning_rate": 1.7274575140626318e-05,
16
  "loss": 0.6796,
17
  "step": 5
 
20
  "epoch": 2.6956521739130435,
21
  "step": 6,
22
  "total_flos": 3.2641218873655296e+16,
23
+ "train_loss": 0.6446646948655447,
24
+ "train_runtime": 174.9578,
25
+ "train_samples_per_second": 1.578,
26
+ "train_steps_per_second": 0.034
27
  }
28
  ],
29
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2072c2a3d329371b4bb7e84363ffd001c562e727dc7072c974ab01eb54c91cf0
3
  size 6097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a766645fa638fefb39182a9a3c4dff0218f23b6ac8611b7b646c151662ea97
3
  size 6097