VERSIL91 commited on
Commit
2709f80
·
verified ·
1 Parent(s): 458046f

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 sha256:97034236b85d8705051666b4950b63d2c64b7155fbe085ddd66d9ccda9dea6f4
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7780de4c737cdc4333ad82131ef674a4d9d5eadf6e90c36b21894997767b6253
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ed65186bd64363c60716a085e319a790b6bff9b352b6878bc085870dd39b249
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa110b0f2bc7e456c1d4a004f505cebc9812272f94e1e96e0fe9bd315b6d8713
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:477dfbc375ce787c0fb87580b02f5d8a564e1e54a5e54bef87785b23172f2094
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e741876d1eca0a88399afff3500f32883025d5cc5badb7d21dd401b48bb9e6ce
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": 0.00014171143124117072,
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": 40.696,
38
  "eval_steps_per_second": 20.348,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1489769318055936.0,
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": 0.00028342286248234143,
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": 40.696,
38
  "eval_steps_per_second": 20.348,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.00021256714686175606,
43
+ "grad_norm": 18.29862403869629,
44
+ "learning_rate": 3e-05,
45
+ "loss": 14.5002,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00028342286248234143,
50
+ "grad_norm": 13.167265892028809,
51
+ "learning_rate": 4e-05,
52
+ "loss": 13.0204,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00028342286248234143,
57
+ "eval_loss": 0.838284432888031,
58
+ "eval_runtime": 585.746,
59
+ "eval_samples_per_second": 40.581,
60
+ "eval_steps_per_second": 20.29,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 3110988870057984.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null