samoline commited on
Commit
117a6b7
·
verified ·
1 Parent(s): 7855c13

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:ba1a91a2c921e67a07997ea867acc4f4b100db44691c2f9774ae8bf8994486af
3
  size 6317744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8732fad3a70520ab505ef439e43e8ff3543e5f6013db7e5886ace4576be5936f
3
  size 6317744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16861a30eca1f8fc26ae4c3b3d2f90e49fc8c6d290abbf1ddccedd67870104e1
3
  size 3420154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9fe6829cb1bb864f547547314dc24741c9c9907bb7aefaf2dba6a22680ee40
3
  size 3420154
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8acd9c3c7698950a48d8431d4b8df7966f76aeab635bf20e8211f02589c5202
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33833de50d67283a280bbe6b9a324fd78a23cccc5f116ff4d4d7957439408d87
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": 8.784027125075763e-06,
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": 29.992,
23
  "eval_steps_per_second": 29.992,
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": 1091775234048.0,
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": 1.7568054250151526e-05,
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": 29.992,
23
  "eval_steps_per_second": 29.992,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 1.7568054250151526e-05,
28
+ "grad_norm": 38.027992248535156,
29
+ "learning_rate": 4e-05,
30
+ "loss": 4.6623,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 1.7568054250151526e-05,
35
+ "eval_loss": 6.904347896575928,
36
+ "eval_runtime": 196.0162,
37
+ "eval_samples_per_second": 30.569,
38
+ "eval_steps_per_second": 30.569,
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": 2183550468096.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null