flytech commited on
Commit
6cee63b
·
1 Parent(s): 8e06889

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 sha256:612d0cd8e57f321f88403f4f45614768b70025f628608916e5fd2cd9d402908d
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2109b17d3075bcc46549572685ddc8e9878c6c72d0f8eab6be5329107070af96
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2acf4d7c5d57285bb03bef169d449f45a00f414b34029a28889830600cc65aab
3
- size 126034399
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca3a240315b371108fcb7002a40b44428e2704d0a3d0fee2bdb7280a753ea3b
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:e647d1e3d8f079c0df95d69b08e31614f4fa92720c95d39f5a0f5e9ff036cd0a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:894edc0af8af25e8fd7f44da70cee3465e97446921206825e927b3090868227a
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": 0.6097560975609756,
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": 3.677,
21
  "eval_steps_per_second": 0.24,
22
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
  "logging_steps": 200,
26
  "max_steps": 2624,
27
  "num_train_epochs": 8,
28
  "save_steps": 200,
29
- "total_flos": 6.459286880256e+16,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.2195121951219512,
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": 3.677,
21
  "eval_steps_per_second": 0.24,
22
  "step": 200
23
+ },
24
+ {
25
+ "epoch": 1.22,
26
+ "learning_rate": 0.0002,
27
+ "loss": 0.0954,
28
+ "step": 400
29
+ },
30
+ {
31
+ "epoch": 1.22,
32
+ "eval_runtime": 74.9815,
33
+ "eval_samples_per_second": 3.681,
34
+ "eval_steps_per_second": 0.24,
35
+ "step": 400
36
  }
37
  ],
38
  "logging_steps": 200,
39
  "max_steps": 2624,
40
  "num_train_epochs": 8,
41
  "save_steps": 200,
42
+ "total_flos": 1.289031438041088e+17,
43
  "trial_name": null,
44
  "trial_params": null
45
  }