duyphu commited on
Commit
e80ec22
·
verified ·
1 Parent(s): 356dc41

Training in progress, step 26, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d0ba80f16c2c94e21775a2856af67517c490b5afe3b70fa1114b06962e15827
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b0f2517c02f83bc1369b687b2c7d09a6483d08f5bac14ea52ace5a911f8851
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0584d08ee5e935d76f6ed797e442004c9715da1fa3031f4dc5943d33ed84df43
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cf2560c9ac719d0b40536645a3970fccfda3bb12e32ed7ca6cc5199b720993e
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": 0.037383177570093455,
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": 10.637,
38
  "eval_steps_per_second": 5.355,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 3920931103703040.0,
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": 0.07476635514018691,
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": 10.637,
38
  "eval_steps_per_second": 5.355,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.043134435657800146,
43
+ "grad_norm": NaN,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 0.393,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.05751258087706686,
50
+ "grad_norm": NaN,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 0.0,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.05751258087706686,
57
+ "eval_loss": NaN,
58
+ "eval_runtime": 13.8031,
59
+ "eval_samples_per_second": 10.65,
60
+ "eval_steps_per_second": 5.361,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.07189072609633357,
65
+ "grad_norm": NaN,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 0.1538,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 7406203195883520.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null