samoline commited on
Commit
81a8a7f
·
verified ·
1 Parent(s): 20162a5

Training in progress, step 2, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ebe4bb207f94bbe3547357f7d6d9d9a3d234755a9561673dc6fbc373f2fd989
3
  size 6359418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63491857bc1b0622de6944cb0469dfbfe20c9220d88b79904471e4f1b43edd92
3
  size 6359418
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a298e5715b056b34aa7c35ee52fddc2bcad190dfc8b88b553f236fca292b9ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca08b34f430cb1db58e5a70661b586b7b096383b4230eceb1b474db199623272
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
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": 0.00013157894736842105,
5
  "eval_steps": 1,
6
- "global_step": 1,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -22,6 +22,21 @@
22
  "eval_samples_per_second": 23.132,
23
  "eval_steps_per_second": 23.132,
24
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 1,
@@ -36,12 +51,12 @@
36
  "should_evaluate": false,
37
  "should_log": false,
38
  "should_save": true,
39
- "should_training_stop": false
40
  },
41
  "attributes": {}
42
  }
43
  },
44
- "total_flos": 2998161899520.0,
45
  "train_batch_size": 1,
46
  "trial_name": null,
47
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0002631578947368421,
5
  "eval_steps": 1,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 23.132,
23
  "eval_steps_per_second": 23.132,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0002631578947368421,
28
+ "grad_norm": NaN,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.0,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0002631578947368421,
35
+ "eval_loss": NaN,
36
+ "eval_runtime": 16.579,
37
+ "eval_samples_per_second": 24.127,
38
+ "eval_steps_per_second": 24.127,
39
+ "step": 2
40
  }
41
  ],
42
  "logging_steps": 1,
 
51
  "should_evaluate": false,
52
  "should_log": false,
53
  "should_save": true,
54
+ "should_training_stop": true
55
  },
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 5996323799040.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null