phungkhaccuong commited on
Commit
6b796bf
·
verified ·
1 Parent(s): 698f487

Training in progress, step 39, 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:efa657266f8effc747dc4edf19be3918f7add5d52570b06e5b7ae045b23c7bad
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3411e5658b009b621408a4d83e81e94f5004cb224cc956abfc4ef9e7ebdba124
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b71759db28b5198317ada0ded18a43353d65000ac9fa92f829cef7d9f618ee32
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6194c87c3c8b88895fa059da50a78aed1ee2aafa20db246337921a2f276b035b
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:581d97fe6008a9750885156089f6b4a1a7e93a5fc902dbf2e649e73c10e3e254
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e2bee1a521f4ebd0f27488d621d4beaa40703e66e4b6904b0a1458fb4f0d90
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.004239188032446093,
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,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.9642,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1195827498319872.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006358782048669139,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.9642,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.004891370806668569,
72
+ "grad_norm": 0.12287212163209915,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.9845,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.004891370806668569,
79
+ "eval_loss": 1.0406432151794434,
80
+ "eval_runtime": 137.355,
81
+ "eval_samples_per_second": 18.805,
82
+ "eval_steps_per_second": 9.406,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005706599274446664,
87
+ "grad_norm": 0.35205531120300293,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.0057,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1758569850470400.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null