End of training
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +40 -0
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 5.5349860191345215,
|
4 |
+
"train_runtime": 2048.5468,
|
5 |
+
"train_samples_per_second": 0.062,
|
6 |
+
"train_steps_per_second": 0.001
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 5.5349860191345215,
|
4 |
+
"train_runtime": 2048.5468,
|
5 |
+
"train_samples_per_second": 0.062,
|
6 |
+
"train_steps_per_second": 0.001
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 100.0,
|
3 |
+
"best_model_checkpoint": "../whisper-NST-TPU-test2/checkpoint-2",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 2,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 0.0,
|
13 |
+
"loss": 5.535,
|
14 |
+
"step": 2
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 4.994277000427246,
|
19 |
+
"eval_runtime": 97.0155,
|
20 |
+
"eval_samples_per_second": 0.01,
|
21 |
+
"eval_steps_per_second": 0.01,
|
22 |
+
"eval_wer": 100.0,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.0,
|
27 |
+
"step": 2,
|
28 |
+
"total_flos": 9234732810240000.0,
|
29 |
+
"train_loss": 5.5349860191345215,
|
30 |
+
"train_runtime": 2048.5468,
|
31 |
+
"train_samples_per_second": 0.062,
|
32 |
+
"train_steps_per_second": 0.001
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"max_steps": 2,
|
36 |
+
"num_train_epochs": 9223372036854775807,
|
37 |
+
"total_flos": 9234732810240000.0,
|
38 |
+
"trial_name": null,
|
39 |
+
"trial_params": null
|
40 |
+
}
|