VERSIL91 commited on
Commit
efc5ebd
·
verified ·
1 Parent(s): 007181e

Training in progress, step 4, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46f5e070caec88ca856302c6731826aa5952e1339d5dc554eff6404de170a65a
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f32f45832644c2ca40db2b1938eaebaffd570646e1a97e9bdb9457bc025a883
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faf5092492cc11f32d2421e5a42a17006c95344f326e6f4570b00d49d97276c6
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aae61cc9117b96137586458f29b7a8e163dd0dec129de7be64f4538f1024511
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:207f66a3c887b74cd1db69c091115f5c25396878c1407db35bd2b1c6a57eecee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c992bec7bad02bc7fd2d5a6b879f5f88896e3c2afafaa49127ee15fcf63f3ab
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
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": 0.03742690058479532,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 4.577,
38
  "eval_steps_per_second": 2.289,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2524561325162496.0,
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": 0.07485380116959064,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 4.577,
38
  "eval_steps_per_second": 2.289,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.056140350877192984,
43
+ "grad_norm": 66.10076141357422,
44
+ "learning_rate": 3e-05,
45
+ "loss": 182.7836,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.07485380116959064,
50
+ "grad_norm": 108.9141616821289,
51
+ "learning_rate": 4e-05,
52
+ "loss": 193.7319,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.07485380116959064,
57
+ "eval_loss": 11.990538597106934,
58
+ "eval_runtime": 21.4072,
59
+ "eval_samples_per_second": 4.204,
60
+ "eval_steps_per_second": 2.102,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 4967685188222976.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null