flytech commited on
Commit
5ca56aa
·
1 Parent(s): 73e9b1f

Training in progress, step 300, 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:afc5f1d993fb9ad740485f32012b466f4513972cc9f7e6ea5f15ac0112dfcb0e
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042b8425ebde2cb12d0526e2606d1e04236d2f3455dc31ac300d60e79381dcf3
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e0a5b7f88ecad00a766b46e9b2eec5247444373addac9a2c2dfa32a6cb65743
3
- size 126034399
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b0526d26f40609f44a30dd2a1b19eb0c73da1390594160e7caec103c5e86a08
3
+ size 126034975
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:870e68660c1c0cbea70ee4766a14a7fcc6c6109ca133c6e5083131ec1208e09b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6816420bd3520cdff06adbda2a2bce14bd8233572776a606d991d5d4d40cca66
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:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
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": 2.4390243902439024,
5
  "eval_steps": 100,
6
- "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -33,13 +33,26 @@
33
  "eval_samples_per_second": 8.515,
34
  "eval_steps_per_second": 0.154,
35
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  }
37
  ],
38
  "logging_steps": 100,
39
  "max_steps": 656,
40
  "num_train_epochs": 8,
41
  "save_steps": 100,
42
- "total_flos": 2.578062876082176e+17,
43
  "trial_name": null,
44
  "trial_params": null
45
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.658536585365854,
5
  "eval_steps": 100,
6
+ "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
33
  "eval_samples_per_second": 8.515,
34
  "eval_steps_per_second": 0.154,
35
  "step": 200
36
+ },
37
+ {
38
+ "epoch": 3.66,
39
+ "learning_rate": 0.0002,
40
+ "loss": 0.0588,
41
+ "step": 300
42
+ },
43
+ {
44
+ "epoch": 3.66,
45
+ "eval_runtime": 32.4061,
46
+ "eval_samples_per_second": 8.517,
47
+ "eval_steps_per_second": 0.154,
48
+ "step": 300
49
  }
50
  ],
51
  "logging_steps": 100,
52
  "max_steps": 656,
53
  "num_train_epochs": 8,
54
  "save_steps": 100,
55
+ "total_flos": 3.867094314123264e+17,
56
  "trial_name": null,
57
  "trial_params": null
58
  }