leixa commited on
Commit
faf7498
·
verified ·
1 Parent(s): 387ba4e

Training in progress, step 15, 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:b38f14f04945602aece259eccdccb4a760d095ccda805bc0fb98947167ba48bb
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3939e27fb282af4053b84009871c1fdab2b0d85bbd2f2fc8b6588dfb8e0f38b9
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e107ec807a474283f5a7e99f3f047363ce553df7ce7d08e914b4a36958b77fd2
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a95022f95a94ce0155c0b2a859be2058be314bc755a7bdf10ebab0e5efeb5bb
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e9d6d75058befc172d955b513ab0168892dc11f97735aa34d08e041b2de55ff
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fdbb6c5c2f8a3babb3fc37d54b607fc9354b33540d06a0b7b5bf287462ca599
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
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": 0.0023449407902450463,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,28 @@
52
  "eval_samples_per_second": 6.544,
53
  "eval_steps_per_second": 0.818,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +93,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 2.57604722884608e+16,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0035174111853675696,
5
  "eval_steps": 5,
6
+ "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 6.544,
53
  "eval_steps_per_second": 0.818,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.0028139289482940555,
58
+ "grad_norm": 1.891883134841919,
59
+ "learning_rate": 9.938441702975689e-05,
60
+ "loss": 2.4376,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.0035174111853675696,
65
+ "grad_norm": 1.4731217622756958,
66
+ "learning_rate": 9.619397662556435e-05,
67
+ "loss": 2.1727,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.0035174111853675696,
72
+ "eval_loss": 0.5438524484634399,
73
+ "eval_runtime": 1097.8515,
74
+ "eval_samples_per_second": 6.542,
75
+ "eval_steps_per_second": 0.818,
76
+ "step": 15
77
  }
78
  ],
79
  "logging_steps": 3,
 
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 3.86407084326912e+16,
97
  "train_batch_size": 8,
98
  "trial_name": null,
99
  "trial_params": null