root commited on
Commit
3335897
·
1 Parent(s): 34eb973

Clean up repo: remove optimizer and training state files for inference-only usage

Browse files
optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bc84e2df8b9992345002ebe0b7949180b364ffb12410d120a3e3196f431fa9c
3
- size 4471062982
 
 
 
 
rng_state_0.pth DELETED
Binary file (15.4 kB)
 
rng_state_1.pth DELETED
Binary file (15.4 kB)
 
rng_state_2.pth DELETED
Binary file (15.4 kB)
 
rng_state_3.pth DELETED
Binary file (15.4 kB)
 
scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4154231fb193d6770822bd3dfc131fe65016a05e3001916be58a400cd9595abe
3
- size 1465
 
 
 
 
trainer_state.json DELETED
@@ -1,83 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.9930555555555556,
6
- "eval_steps": 500,
7
- "global_step": 715,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.1388888888888889,
14
- "grad_norm": 11.897926330566406,
15
- "learning_rate": 8.9010989010989e-06,
16
- "loss": 0.0858,
17
- "step": 100
18
- },
19
- {
20
- "epoch": 0.2777777777777778,
21
- "grad_norm": 10.644397735595703,
22
- "learning_rate": 7.680097680097681e-06,
23
- "loss": 0.0712,
24
- "step": 200
25
- },
26
- {
27
- "epoch": 0.4166666666666667,
28
- "grad_norm": 4.836203098297119,
29
- "learning_rate": 6.45909645909646e-06,
30
- "loss": 0.0571,
31
- "step": 300
32
- },
33
- {
34
- "epoch": 0.5555555555555556,
35
- "grad_norm": 7.090342044830322,
36
- "learning_rate": 5.2380952380952384e-06,
37
- "loss": 0.0588,
38
- "step": 400
39
- },
40
- {
41
- "epoch": 0.6944444444444444,
42
- "grad_norm": 2.936511278152466,
43
- "learning_rate": 4.017094017094018e-06,
44
- "loss": 0.0481,
45
- "step": 500
46
- },
47
- {
48
- "epoch": 0.8333333333333334,
49
- "grad_norm": 16.002599716186523,
50
- "learning_rate": 2.796092796092796e-06,
51
- "loss": 0.0465,
52
- "step": 600
53
- },
54
- {
55
- "epoch": 0.9722222222222222,
56
- "grad_norm": 6.044346809387207,
57
- "learning_rate": 1.5750915750915753e-06,
58
- "loss": 0.0375,
59
- "step": 700
60
- }
61
- ],
62
- "logging_steps": 100,
63
- "max_steps": 828,
64
- "num_input_tokens_seen": 0,
65
- "num_train_epochs": 2,
66
- "save_steps": 500,
67
- "stateful_callbacks": {
68
- "TrainerControl": {
69
- "args": {
70
- "should_epoch_stop": false,
71
- "should_evaluate": false,
72
- "should_log": false,
73
- "should_save": true,
74
- "should_training_stop": false
75
- },
76
- "attributes": {}
77
- }
78
- },
79
- "total_flos": 0.0,
80
- "train_batch_size": 32,
81
- "trial_name": null,
82
- "trial_params": null
83
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1c6aa472f2c20b3caa1a52a39018187095921be2178aa0b6ecaaaca96bcbaa3
3
- size 6225