VERSIL91 commited on
Commit
b57dff5
·
verified ·
1 Parent(s): 242c597

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:a29bace7ea171c8f3f2ed3ffaa1f9753627d70ebbf591b605a003a4affd34a2c
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7cd0c0bdef31e6d5d4c3294d41edab1ccfefa98a84d44c9ab31d6ec007e0b6
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3695f0d2cfc27bfc140cbc830fe590fff1416d589c83e517fef3decd3032f566
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fff1b251670f40044114fd985062bedc527c09ce2b3d7222b2250581723d9c5
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf01f44474d740cb50fb457c5886229e351491327c1b29b109a62f306b26239
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f1b71931fd3de4c1deb7107c2626b268932ef752bc861abaa06d80432a643b
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": 0.0010988256301078224,
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": 7.288,
38
  "eval_steps_per_second": 3.644,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4907647673303040.0,
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": 0.0021976512602156447,
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": 7.288,
38
  "eval_steps_per_second": 3.644,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0016482384451617334,
43
+ "grad_norm": 1.0694772005081177,
44
+ "learning_rate": 3e-05,
45
+ "loss": 27.0594,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0021976512602156447,
50
+ "grad_norm": 1.2885613441467285,
51
+ "learning_rate": 4e-05,
52
+ "loss": 26.5673,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0021976512602156447,
57
+ "eval_loss": 1.7147361040115356,
58
+ "eval_runtime": 1172.5782,
59
+ "eval_samples_per_second": 2.615,
60
+ "eval_steps_per_second": 1.307,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 9815295346606080.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null