VERSIL91 commited on
Commit
ffcefd7
·
verified ·
1 Parent(s): d61268c

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 sha256:44bb5dbeb8f2a8287f0bb8384b9101e519ab15e259b30daf05ee8c8cf7c10415
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99663b5ab2d829fa3d53b5d1a132c9ee04ee03cbad030671cfbb87e03e5f14f
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56c123fdfcd092db9f39766889560b09688cb48347195401f66a822b39d3a2d4
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab613ae9a194c8f0e018c16baf64a41067be70e4148fb81a421d03ff2393c59
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:c46e88b4c6d353657e53552d7e0de44c36fe47ff4c4a5c23dafe2255812f99e9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7c3dcfd2fbfcccbf5177669f5b109776dfbae391c64a8d0d5e2326b72c5b68
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": 0.0005675268245100648,
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": 3.353,
38
  "eval_steps_per_second": 1.676,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1302986508730368.0,
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": 0.0011350536490201295,
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": 3.353,
38
  "eval_steps_per_second": 1.676,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0008512902367650971,
43
+ "grad_norm": 50.551979064941406,
44
+ "learning_rate": 3e-05,
45
+ "loss": 68.4265,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0011350536490201295,
50
+ "grad_norm": 50.849205017089844,
51
+ "learning_rate": 4e-05,
52
+ "loss": 87.0254,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0011350536490201295,
57
+ "eval_loss": 5.592475891113281,
58
+ "eval_runtime": 992.8782,
59
+ "eval_samples_per_second": 5.979,
60
+ "eval_steps_per_second": 2.989,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2605973017460736.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null