tuanna08go commited on
Commit
782d37f
·
verified ·
1 Parent(s): 581b3d9

Training in progress, step 26, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68e30d7c2d0188913f57e69b55ab1537c6fbd49e39a907087e78d935bef083b7
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a8bcab1f5a8b0782bedce8473e2b45ae32c810dce7a54d54ff1d45c511138a
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63cd24238d688c8d9b89b7d810336b7c5d0093e69eb03f22da93949532954c36
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d893da68a61abb77449abb6589e1c26bd9585c3485468f503dae7233c85a6ac
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41e8229120dce69fa1081c29f9ca7f12647fb8db9c60a1f8dce12e8d0bda6beb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea402b9b27c3cc250416823d1fd916c155c6766d61390bd38b5912be5e16fc65
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0009571139333701454,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 23.313,
38
  "eval_steps_per_second": 11.659,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 650126529921024.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0019142278667402908,
5
  "eval_steps": 10,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 23.313,
38
  "eval_steps_per_second": 11.659,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0011043622308117063,
43
+ "grad_norm": 5.180222034454346,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 3.4088,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.0014724829744156083,
50
+ "grad_norm": 5.636661529541016,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 3.3155,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.0014724829744156083,
57
+ "eval_loss": 3.170792818069458,
58
+ "eval_runtime": 244.3666,
59
+ "eval_samples_per_second": 23.403,
60
+ "eval_steps_per_second": 11.704,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.0018406037180195105,
65
+ "grad_norm": 4.489249229431152,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 3.0083,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 1300253059842048.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null