robiulawaldev commited on
Commit
a46ebdf
·
verified ·
1 Parent(s): 4721229

Training in progress, step 42, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e124b45ee1df21c68eb148c7df8bacc371efa2fb6216855fea877456cc02de6
3
  size 147770496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c30a91dfe450570125c38ead8325c3181ce4dfa0ff79da1572183a9b969bc8
3
  size 147770496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6b195f28f94e374b282cb0ab6fe261d0d3711cbb0575f65a3ace5145ccedce
3
  size 75471860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b143646ed979c314d570266e9b3640d3b565f36fa46d2756fafb2c49ba765b
3
  size 75471860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b13ce8308266d915bd25b0b391764f5c10e112e199f7f6edacd41d5676538b0a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb415ea26e870302de4384a029ef7ff77e384ddb696ca258894875114dc0a21
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ed58e5b5053e09a44cd1fe67ab0f07cc790b003abec6db1f957ea4f926e4423
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43352a0ea01b8f309df99bb65027960564fe5f2f452a04b8b6c955b0ecfed4cf
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": 0.02125237191650854,
5
  "eval_steps": 14,
6
- "global_step": 28,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,28 @@
45
  "eval_samples_per_second": 48.635,
46
  "eval_steps_per_second": 24.318,
47
  "step": 28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +86,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 463547154825216.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.031878557874762806,
5
  "eval_steps": 14,
6
+ "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 48.635,
46
  "eval_steps_per_second": 24.318,
47
  "step": 28
48
+ },
49
+ {
50
+ "epoch": 0.022770398481973434,
51
+ "grad_norm": 4.151969909667969,
52
+ "learning_rate": 0.0002,
53
+ "loss": 1.1996,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.030360531309297913,
58
+ "grad_norm": 13.053388595581055,
59
+ "learning_rate": 0.0002,
60
+ "loss": 1.1524,
61
+ "step": 40
62
+ },
63
+ {
64
+ "epoch": 0.031878557874762806,
65
+ "eval_loss": 1.0414668321609497,
66
+ "eval_runtime": 5.6278,
67
+ "eval_samples_per_second": 49.397,
68
+ "eval_steps_per_second": 24.699,
69
+ "step": 42
70
  }
71
  ],
72
  "logging_steps": 10,
 
86
  "attributes": {}
87
  }
88
  },
89
+ "total_flos": 695320732237824.0,
90
  "train_batch_size": 2,
91
  "trial_name": null,
92
  "trial_params": null