samoline commited on
Commit
f80418f
·
verified ·
1 Parent(s): 9c01dd2

Training in progress, step 2, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e15ecffb91cfb9c8927e2d031f0a830eb0dbc23bb6ec0edd3f95dbacaf4718f
3
  size 40421816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d1fcd5cbf0a058004aebf54267f49e9b6fb7d6c48f5ba6e2c781458906056ae
3
  size 40421816
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04e1efdfd21902f0818d9b47ba9edc862fbd0d48a006646dd47f453a5ef25bc4
3
  size 21590212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cc9d746c8890cc80ed34f2ec0941b8a853b53818e76a0e94dc2574ecb667fcf
3
  size 21590212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ced82cc9952b6efa759184ffd26f74ce2e2e1b029f2ef22b38a13f001d18dde
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ffa0112df1b9ae96a155c4854192d2e728be2c4ed8384be17378a077ee3ee82
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": 6.50110518788194e-05,
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": 13.12,
23
  "eval_steps_per_second": 13.12,
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": 21751946280960.0,
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": 0.0001300221037576388,
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": 13.12,
23
  "eval_steps_per_second": 13.12,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0001300221037576388,
28
+ "grad_norm": 0.9349897503852844,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.46,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0001300221037576388,
35
+ "eval_loss": 3.7115304470062256,
36
+ "eval_runtime": 61.5016,
37
+ "eval_samples_per_second": 13.17,
38
+ "eval_steps_per_second": 13.17,
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": 43503892561920.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null