mgh6 commited on
Commit
cc0ce70
·
verified ·
1 Parent(s): f1b8feb

Training in progress, epoch 1, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ede89cd7420b342554cf586111ef386bc4803fe1942c8c752e713c75eb639884
3
  size 2610104820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6697b655f4d18a8afd09bb9096be4f1a913a0271400253530af3111df7c5aab
3
  size 2610104820
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a83ac9d504c4f5a9d0b3ec6c9d0ab931281b9695216ad64ae558fdd4e9634d9
3
  size 5210004271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3379d3b2136cd08b2e8087edaea7dccb8c45d272e6cb1ff778c0d48eb147e4c
3
  size 5210004271
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9080aea5181d3066ab765d04bc9819f089e9674161d5e56c8bf2b7c839212160
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b30662bbeef6882959d6b6e1aa2b4df9a78ead5291d63da14771bbe171fced3d
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fd6739d9b468767c726a8685cd4457152a8323bb7a81cf6908a01dd282a18e8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09d30be9f305b7f8107cd63b7c58a0bc8abb2ce2c79242a145a2911b000d0ccd
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3716533184051514,
3
- "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-244",
4
- "epoch": 0.9960454139558618,
5
  "eval_steps": 500,
6
- "global_step": 244,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -22,6 +22,21 @@
22
  "eval_samples_per_second": 32.821,
23
  "eval_steps_per_second": 16.411,
24
  "step": 244
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 500,
 
1
  {
2
+ "best_metric": 1.3613533973693848,
3
+ "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-488",
4
+ "epoch": 1.9960454139558617,
5
  "eval_steps": 500,
6
+ "global_step": 488,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 32.821,
23
  "eval_steps_per_second": 16.411,
24
  "step": 244
25
+ },
26
+ {
27
+ "epoch": 1.9960454139558617,
28
+ "grad_norm": 0.10088465362787247,
29
+ "learning_rate": 0.0009666666666666667,
30
+ "loss": 1.373,
31
+ "step": 488
32
+ },
33
+ {
34
+ "epoch": 1.9960454139558617,
35
+ "eval_loss": 1.3613533973693848,
36
+ "eval_runtime": 25.126,
37
+ "eval_samples_per_second": 32.874,
38
+ "eval_steps_per_second": 16.437,
39
+ "step": 488
40
  }
41
  ],
42
  "logging_steps": 500,