Takeshi10Days commited on
Commit
e27d64b
1 Parent(s): ff17baf

Training in progress, step 500

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49ea815675a34cbac9041de1da9a12ba61041e70f135f09a49e7225458df2955
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2eaea334426df63ce8a8325639be5c5b51b1220af4178809eb6e46d500d52d
3
  size 268290900
run-1/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:143f04053d04d75ffaa4e7dd07d1604b3bfb77a79f178c1e1830668381f8867c
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2eaea334426df63ce8a8325639be5c5b51b1220af4178809eb6e46d500d52d
3
  size 268290900
run-1/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:436d2db236d749c9f1be30b3bc1fb3d426342395688e845147f9e431230052a5
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564d115631b22c472c2359b96280732e3452cb8774d90869d0b201766c47312c
3
  size 536643898
run-1/checkpoint-500/trainer_state.json CHANGED
@@ -10,17 +10,17 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.20451311767101288,
14
- "eval_runtime": 3.3051,
15
- "eval_samples_per_second": 937.956,
16
- "eval_steps_per_second": 19.667,
17
  "step": 318
18
  },
19
  {
20
  "epoch": 1.57,
21
- "grad_norm": 0.5476486682891846,
22
  "learning_rate": 1.371069182389937e-05,
23
- "loss": 0.3209,
24
  "step": 500
25
  }
26
  ],
@@ -33,8 +33,8 @@
33
  "train_batch_size": 48,
34
  "trial_name": null,
35
  "trial_params": {
36
- "alpha": 0.6466886043446713,
37
- "num_train_epochs": 8,
38
- "temperature": 13
39
  }
40
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.19908840954303741,
14
+ "eval_runtime": 3.4704,
15
+ "eval_samples_per_second": 893.271,
16
+ "eval_steps_per_second": 18.73,
17
  "step": 318
18
  },
19
  {
20
  "epoch": 1.57,
21
+ "grad_norm": 0.5476423501968384,
22
  "learning_rate": 1.371069182389937e-05,
23
+ "loss": 0.3126,
24
  "step": 500
25
  }
26
  ],
 
33
  "train_batch_size": 48,
34
  "trial_name": null,
35
  "trial_params": {
36
+ "alpha": 0.20320499954717708,
37
+ "num_train_epochs": 6,
38
+ "temperature": 19
39
  }
40
  }
run-1/checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:787f17d4b84c91e9b55e9fd77b9b388ac3a69fb2918ab4a982181007a952d0ef
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f382a675383c3cd8b7905ca7bec8595abcd4866f9bbfeb75d8c432240eabdc
3
  size 4984
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67043ee677699277df7121e843ef614cde58c5bac2c9528a63210454b8dcf1c1
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f382a675383c3cd8b7905ca7bec8595abcd4866f9bbfeb75d8c432240eabdc
3
  size 4984