duyphu commited on
Commit
321e6a8
·
verified ·
1 Parent(s): 2d0d334

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 sha256:0253a410fb9b6ddf2a21b6ebd630b145a91993d42e14f63b85848f1c2a96d813
3
  size 31064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b284cb4a4c46d4ce14cb11ca7f2e754568bfa8349eafd682b6acc996e3a9c70a
3
  size 31064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7df7959a791631ebffd3fedd7dc39878032a11ddfb13f03519a3e26ac4a6bf86
3
  size 71718
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b08f8ca31053f8ca4eea805615c609e71c600812ca7d46c840a3e2fe5e7cb846
3
  size 71718
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
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": 0.0003651557178469857,
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": 170.092,
38
  "eval_steps_per_second": 85.046,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 577458339840.0,
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": 0.0007303114356939714,
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": 170.092,
38
  "eval_steps_per_second": 85.046,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0004213335205926758,
43
+ "grad_norm": 0.288252592086792,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 41.5117,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.0005617780274569011,
50
+ "grad_norm": 0.18418413400650024,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 41.5029,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.0005617780274569011,
57
+ "eval_loss": 10.376041412353516,
58
+ "eval_runtime": 89.2859,
59
+ "eval_samples_per_second": 167.888,
60
+ "eval_steps_per_second": 83.944,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.0007022225343211264,
65
+ "grad_norm": 0.22784556448459625,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 41.5063,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 1142084272128.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null