End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +64 -0
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.6546754837036133,
|
4 |
+
"eval_runtime": 62.1602,
|
5 |
+
"eval_samples": 1112,
|
6 |
+
"eval_samples_per_second": 17.889,
|
7 |
+
"eval_steps_per_second": 4.472,
|
8 |
+
"eval_wer": 0.7824215246636771,
|
9 |
+
"train_loss": 3.913738654210017,
|
10 |
+
"train_runtime": 2210.4533,
|
11 |
+
"train_samples": 3336,
|
12 |
+
"train_samples_per_second": 7.546,
|
13 |
+
"train_steps_per_second": 0.235
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.6546754837036133,
|
4 |
+
"eval_runtime": 62.1602,
|
5 |
+
"eval_samples": 1112,
|
6 |
+
"eval_samples_per_second": 17.889,
|
7 |
+
"eval_steps_per_second": 4.472,
|
8 |
+
"eval_wer": 0.7824215246636771
|
9 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3850717489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48bfecbbd1295259ac4b8cab03b279602178ca411abad06910dcd60a2afda55f
|
3 |
size 3850717489
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 3.913738654210017,
|
4 |
+
"train_runtime": 2210.4533,
|
5 |
+
"train_samples": 3336,
|
6 |
+
"train_samples_per_second": 7.546,
|
7 |
+
"train_steps_per_second": 0.235
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.997601918465228,
|
5 |
+
"global_step": 520,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.96,
|
12 |
+
"learning_rate": 6.533333333333334e-06,
|
13 |
+
"loss": 11.216,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.92,
|
18 |
+
"learning_rate": 1.3200000000000002e-05,
|
19 |
+
"loss": 3.4158,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.88,
|
24 |
+
"learning_rate": 1.9866666666666667e-05,
|
25 |
+
"loss": 2.4363,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.84,
|
30 |
+
"learning_rate": 1.1090909090909092e-05,
|
31 |
+
"loss": 1.6274,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 4.81,
|
36 |
+
"learning_rate": 2.0000000000000003e-06,
|
37 |
+
"loss": 1.3883,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 4.81,
|
42 |
+
"eval_loss": 0.6559479236602783,
|
43 |
+
"eval_runtime": 61.7219,
|
44 |
+
"eval_samples_per_second": 18.016,
|
45 |
+
"eval_steps_per_second": 4.504,
|
46 |
+
"eval_wer": 0.7843946188340807,
|
47 |
+
"step": 500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 5.0,
|
51 |
+
"step": 520,
|
52 |
+
"total_flos": 7.17353684308089e+18,
|
53 |
+
"train_loss": 3.913738654210017,
|
54 |
+
"train_runtime": 2210.4533,
|
55 |
+
"train_samples_per_second": 7.546,
|
56 |
+
"train_steps_per_second": 0.235
|
57 |
+
}
|
58 |
+
],
|
59 |
+
"max_steps": 520,
|
60 |
+
"num_train_epochs": 5,
|
61 |
+
"total_flos": 7.17353684308089e+18,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": null
|
64 |
+
}
|