End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +61 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.98,
|
| 3 |
+
"eval_loss": 0.5682483315467834,
|
| 4 |
+
"eval_runtime": 68.6413,
|
| 5 |
+
"eval_samples": 1647,
|
| 6 |
+
"eval_samples_per_second": 23.994,
|
| 7 |
+
"eval_steps_per_second": 0.758,
|
| 8 |
+
"eval_wer": 0.5738943928097232,
|
| 9 |
+
"train_loss": 3.53821102189429,
|
| 10 |
+
"train_runtime": 13547.1548,
|
| 11 |
+
"train_samples": 3478,
|
| 12 |
+
"train_samples_per_second": 3.851,
|
| 13 |
+
"train_steps_per_second": 0.03
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.98,
|
| 3 |
+
"eval_loss": 0.5682483315467834,
|
| 4 |
+
"eval_runtime": 68.6413,
|
| 5 |
+
"eval_samples": 1647,
|
| 6 |
+
"eval_samples_per_second": 23.994,
|
| 7 |
+
"eval_steps_per_second": 0.758,
|
| 8 |
+
"eval_wer": 0.5738943928097232
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.98,
|
| 3 |
+
"train_loss": 3.53821102189429,
|
| 4 |
+
"train_runtime": 13547.1548,
|
| 5 |
+
"train_samples": 3478,
|
| 6 |
+
"train_samples_per_second": 3.851,
|
| 7 |
+
"train_steps_per_second": 0.03
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.981818181818182,
|
| 5 |
+
"global_step": 405,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 3.69,
|
| 12 |
+
"eval_loss": 3.536450147628784,
|
| 13 |
+
"eval_runtime": 68.3549,
|
| 14 |
+
"eval_samples_per_second": 24.095,
|
| 15 |
+
"eval_steps_per_second": 0.761,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 7.4,
|
| 21 |
+
"eval_loss": 2.934115171432495,
|
| 22 |
+
"eval_runtime": 67.8143,
|
| 23 |
+
"eval_samples_per_second": 24.287,
|
| 24 |
+
"eval_steps_per_second": 0.767,
|
| 25 |
+
"eval_wer": 0.9998978653865795,
|
| 26 |
+
"step": 200
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 11.11,
|
| 30 |
+
"eval_loss": 0.6993811130523682,
|
| 31 |
+
"eval_runtime": 68.1937,
|
| 32 |
+
"eval_samples_per_second": 24.152,
|
| 33 |
+
"eval_steps_per_second": 0.763,
|
| 34 |
+
"eval_wer": 0.68409764069043,
|
| 35 |
+
"step": 300
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 14.8,
|
| 39 |
+
"eval_loss": 0.5623299479484558,
|
| 40 |
+
"eval_runtime": 67.3052,
|
| 41 |
+
"eval_samples_per_second": 24.471,
|
| 42 |
+
"eval_steps_per_second": 0.773,
|
| 43 |
+
"eval_wer": 0.5792053927075886,
|
| 44 |
+
"step": 400
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 14.98,
|
| 48 |
+
"step": 405,
|
| 49 |
+
"total_flos": 6.92765272380492e+18,
|
| 50 |
+
"train_loss": 3.53821102189429,
|
| 51 |
+
"train_runtime": 13547.1548,
|
| 52 |
+
"train_samples_per_second": 3.851,
|
| 53 |
+
"train_steps_per_second": 0.03
|
| 54 |
+
}
|
| 55 |
+
],
|
| 56 |
+
"max_steps": 405,
|
| 57 |
+
"num_train_epochs": 15,
|
| 58 |
+
"total_flos": 6.92765272380492e+18,
|
| 59 |
+
"trial_name": null,
|
| 60 |
+
"trial_params": null
|
| 61 |
+
}
|