flytech commited on
Commit
5a19fb2
1 Parent(s): 6d8161f

Training in progress, step 400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ada79057b9c4e1e943abf5b7525a076fc89b63b6ea393a5c88c3776373a974e
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201ddb356476f4c10cca25e1fb2273dacf5c857b179880fbe9d4d9f12168a7be
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:125a855dcbbb1e4f345f542698a30762dd78dd37be94931579369ffc522f7a1e
3
- size 126034399
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a1593446734f668bdee611a1e57018ce79abb89e9b3ab6039795ead19b1e6d
3
+ size 126034975
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed40df4fdeb37f0cef279b2d6865cde74504b29be5b7b6f37e04ee1246fbdd06
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67adb1b2bad2d2abd8a8d3e8645a20ba750d688661b7a5316aa49ac1a4fcc9d8
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.5376344086021505,
5
  "eval_steps": 200,
6
- "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -20,13 +20,26 @@
20
  "eval_samples_per_second": 2.75,
21
  "eval_steps_per_second": 0.176,
22
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
  "logging_steps": 200,
26
  "max_steps": 2232,
27
  "num_train_epochs": 6,
28
  "save_steps": 200,
29
- "total_flos": 9.537540784128e+16,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.075268817204301,
5
  "eval_steps": 200,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
20
  "eval_samples_per_second": 2.75,
21
  "eval_steps_per_second": 0.176,
22
  "step": 200
23
+ },
24
+ {
25
+ "epoch": 1.08,
26
+ "learning_rate": 0.0002,
27
+ "loss": 0.077,
28
+ "step": 400
29
+ },
30
+ {
31
+ "epoch": 1.08,
32
+ "eval_runtime": 113.8308,
33
+ "eval_samples_per_second": 2.75,
34
+ "eval_steps_per_second": 0.176,
35
+ "step": 400
36
  }
37
  ],
38
  "logging_steps": 200,
39
  "max_steps": 2232,
40
  "num_train_epochs": 6,
41
  "save_steps": 200,
42
+ "total_flos": 1.905421819779072e+17,
43
  "trial_name": null,
44
  "trial_params": null
45
  }