duyphu commited on
Commit
9fd48c2
·
verified ·
1 Parent(s): 379bb60

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:d875fc7d0093703af99d08c1ab1ee618e7cfead8afaff4454563c283bbc118e6
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c1dc18906179a12ed0c3b1a3ed21ed1b2327cdb2d797fd9aacbf9cf8edc724a
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b201e248f25210c937d128c53a1d3e2a3e03444a4cf869d6ce70fe9bcc6f745
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64ad16e7c66ef8a8876f311781fb728d9104a5678baacb211cfd6067723240ee
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28e6579874485b23c70c75df1980183043c6d4000a5e71c69e02f035621c4945
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e13fa025c9a824f965c7766c9716c9550812a29eb06c59107269912ce31e69
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": 0.0004027978961556039,
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": 9.319,
38
  "eval_steps_per_second": 4.66,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4243144027668480.0,
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": 0.0008055957923112078,
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": 9.319,
38
  "eval_steps_per_second": 4.66,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0004647668032564661,
43
+ "grad_norm": 0.29153722524642944,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 1.1034,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.0006196890710086214,
50
+ "grad_norm": 0.31050845980644226,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 1.0061,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.0006196890710086214,
57
+ "eval_loss": 1.0127846002578735,
58
+ "eval_runtime": 1456.8345,
59
+ "eval_samples_per_second": 9.328,
60
+ "eval_steps_per_second": 4.664,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.0007746113387607767,
65
+ "grad_norm": 0.338260293006897,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 1.0445,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 8445092482252800.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null