Femboyuwu2000 commited on
Commit
ad50219
1 Parent(s): 4e01441

Training in progress, step 40, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6a34638443619a0074ff65dd497b16f574e80c9fdb420e3c4296436112df978
3
  size 4644026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b397010904d2981a0836df557bcee1905ad60498f9639327b19017693880d7c
3
  size 4644026
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5dd73064a7e6156867bfe7cc42d099f9b3ca8a81e8092e75ee1ad1a149c9681
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6370a8be0528273ca811acd9c2bcf74f85b802ea1813f278d9313dd42676b8dc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:064312e6375f494574ea3d2e75c4bb8dc97a4b36316db34a10f092589094ee40
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b000d8ec0df62079ef67fc64937bd9acc7a1f4d0e9018e1bef629d1be460950
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": 6.226020094479855e-05,
5
  "eval_steps": 500,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -14,6 +14,13 @@
14
  "learning_rate": 9.999999999999999e-06,
15
  "loss": 4.7404,
16
  "step": 20
 
 
 
 
 
 
 
17
  }
18
  ],
19
  "logging_steps": 20,
@@ -21,7 +28,7 @@
21
  "num_input_tokens_seen": 0,
22
  "num_train_epochs": 1,
23
  "save_steps": 20,
24
- "total_flos": 276350185052160.0,
25
  "train_batch_size": 1,
26
  "trial_name": null,
27
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0001245204018895971,
5
  "eval_steps": 500,
6
+ "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
14
  "learning_rate": 9.999999999999999e-06,
15
  "loss": 4.7404,
16
  "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": NaN,
21
+ "learning_rate": 1.9999999999999998e-05,
22
+ "loss": 4.6952,
23
+ "step": 40
24
  }
25
  ],
26
  "logging_steps": 20,
 
28
  "num_input_tokens_seen": 0,
29
  "num_train_epochs": 1,
30
  "save_steps": 20,
31
+ "total_flos": 414944621529600.0,
32
  "train_batch_size": 1,
33
  "trial_name": null,
34
  "trial_params": null