mgh6 commited on
Commit
558734f
1 Parent(s): 6c56828

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d847a35f3873099d98493e726b742cc28adeb61a532c8679bdb4a5818e20ebab
3
  size 1442155488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49ab817dccb2991dc10799e87b7b5ef8d911c91af4927c7af0915d16b8e08a3
3
  size 1442155488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a0e4c6eaa26d24ce4860ebb1a734eb6a7ac278634776e3319027edcc734ffe8
3
  size 2884319911
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea905ee81b74b430929b39f11eddb929c094f9c43b6ace050891e9dbe4cd06fe
3
  size 2884319911
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d20042fc4c8d7c69d252d0962c45eb770fda78670259941efb34d492469c486
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63fa71e984a3d0e3b5714c0ad917239c336c70ab5692dc973e2d63476c86b3e0
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f4d478b2dc67950c1eefd3798c980a03185bb9419b0025d6be485e59318e5bb
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed2d3d37bbc3f87f1bf9cb4cde4cce4d96490c6bba47f55003e23f806d7adea
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.2,
5
  "eval_steps": 500,
6
- "global_step": 1500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -49,6 +49,20 @@
49
  "eval_samples_per_second": 16.825,
50
  "eval_steps_per_second": 2.103,
51
  "step": 1500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  }
53
  ],
54
  "logging_steps": 500,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.6,
5
  "eval_steps": 500,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
49
  "eval_samples_per_second": 16.825,
50
  "eval_steps_per_second": 2.103,
51
  "step": 1500
52
+ },
53
+ {
54
+ "epoch": 1.6,
55
+ "learning_rate": 0.0009466666666666667,
56
+ "loss": 128776.992,
57
+ "step": 2000
58
+ },
59
+ {
60
+ "epoch": 1.6,
61
+ "eval_loss": 128457.265625,
62
+ "eval_runtime": 1211.4822,
63
+ "eval_samples_per_second": 16.508,
64
+ "eval_steps_per_second": 2.064,
65
+ "step": 2000
66
  }
67
  ],
68
  "logging_steps": 500,