mgh6 commited on
Commit
3ff3420
·
verified ·
1 Parent(s): dcd12ae

Training in progress, step 1500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0d5b70e245438e166b96f618cde7523d1a18886aad9728e90c28031a3a77b49
3
  size 1442155488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d847a35f3873099d98493e726b742cc28adeb61a532c8679bdb4a5818e20ebab
3
  size 1442155488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:582e16a1da51339ba33a94e5700cf386e1f505c219e75be970158702084828ce
3
  size 2884319911
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0e4c6eaa26d24ce4860ebb1a734eb6a7ac278634776e3319027edcc734ffe8
3
  size 2884319911
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:076446b2848c20d501548c01c0270f7d595321cf5d08de360d97df6dda4d5978
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d20042fc4c8d7c69d252d0962c45eb770fda78670259941efb34d492469c486
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e358772ebc9ad6cfde934716864f9a69585d3a037926074d0d518226baec18ce
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4d478b2dc67950c1eefd3798c980a03185bb9419b0025d6be485e59318e5bb
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": 0.8,
5
  "eval_steps": 500,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -35,6 +35,20 @@
35
  "eval_samples_per_second": 16.667,
36
  "eval_steps_per_second": 2.083,
37
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  }
39
  ],
40
  "logging_steps": 500,
 
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,
 
35
  "eval_samples_per_second": 16.667,
36
  "eval_steps_per_second": 2.083,
37
  "step": 1000
38
+ },
39
+ {
40
+ "epoch": 1.2,
41
+ "learning_rate": 0.00096,
42
+ "loss": 129394.928,
43
+ "step": 1500
44
+ },
45
+ {
46
+ "epoch": 1.2,
47
+ "eval_loss": 129025.2265625,
48
+ "eval_runtime": 1188.6216,
49
+ "eval_samples_per_second": 16.825,
50
+ "eval_steps_per_second": 2.103,
51
+ "step": 1500
52
  }
53
  ],
54
  "logging_steps": 500,