Delete trainer_state.json
Browse files- trainer_state.json +0 -61
trainer_state.json
DELETED
@@ -1,61 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.0,
|
5 |
-
"global_step": 3068,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.33,
|
12 |
-
"learning_rate": 4.185136897001304e-05,
|
13 |
-
"loss": 0.7763,
|
14 |
-
"step": 500
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.65,
|
18 |
-
"learning_rate": 3.370273794002607e-05,
|
19 |
-
"loss": 0.6385,
|
20 |
-
"step": 1000
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.98,
|
24 |
-
"learning_rate": 2.5554106910039117e-05,
|
25 |
-
"loss": 0.6041,
|
26 |
-
"step": 1500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 1.3,
|
30 |
-
"learning_rate": 1.740547588005215e-05,
|
31 |
-
"loss": 0.5271,
|
32 |
-
"step": 2000
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 1.63,
|
36 |
-
"learning_rate": 9.25684485006519e-06,
|
37 |
-
"loss": 0.515,
|
38 |
-
"step": 2500
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 1.96,
|
42 |
-
"learning_rate": 1.108213820078227e-06,
|
43 |
-
"loss": 0.5088,
|
44 |
-
"step": 3000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 2.0,
|
48 |
-
"step": 3068,
|
49 |
-
"total_flos": 5.166258268431053e+16,
|
50 |
-
"train_loss": 0.592957808732054,
|
51 |
-
"train_runtime": 5580.5786,
|
52 |
-
"train_samples_per_second": 140.739,
|
53 |
-
"train_steps_per_second": 0.55
|
54 |
-
}
|
55 |
-
],
|
56 |
-
"max_steps": 3068,
|
57 |
-
"num_train_epochs": 2,
|
58 |
-
"total_flos": 5.166258268431053e+16,
|
59 |
-
"trial_name": null,
|
60 |
-
"trial_params": null
|
61 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|