End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +49 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.18222478032112122,
|
| 4 |
+
"eval_runtime": 94.9345,
|
| 5 |
+
"eval_samples": 1647,
|
| 6 |
+
"eval_samples_per_second": 17.349,
|
| 7 |
+
"eval_steps_per_second": 8.68,
|
| 8 |
+
"eval_wer": 0.14227351649474007,
|
| 9 |
+
"train_loss": 1.2537303696030295,
|
| 10 |
+
"train_runtime": 320.3475,
|
| 11 |
+
"train_samples": 3478,
|
| 12 |
+
"train_samples_per_second": 10.857,
|
| 13 |
+
"train_steps_per_second": 1.355
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.18222478032112122,
|
| 4 |
+
"eval_runtime": 94.9345,
|
| 5 |
+
"eval_samples": 1647,
|
| 6 |
+
"eval_samples_per_second": 17.349,
|
| 7 |
+
"eval_steps_per_second": 8.68,
|
| 8 |
+
"eval_wer": 0.14227351649474007
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.2537303696030295,
|
| 4 |
+
"train_runtime": 320.3475,
|
| 5 |
+
"train_samples": 3478,
|
| 6 |
+
"train_samples_per_second": 10.857,
|
| 7 |
+
"train_steps_per_second": 1.355
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9982748706152962,
|
| 5 |
+
"global_step": 434,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.23,
|
| 12 |
+
"learning_rate": 3.7500000000000005e-08,
|
| 13 |
+
"loss": 1.2688,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.46,
|
| 18 |
+
"learning_rate": 7.500000000000001e-08,
|
| 19 |
+
"loss": 1.2572,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.69,
|
| 24 |
+
"learning_rate": 1.125e-07,
|
| 25 |
+
"loss": 1.2306,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.92,
|
| 30 |
+
"learning_rate": 1.5000000000000002e-07,
|
| 31 |
+
"loss": 1.2477,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"step": 434,
|
| 37 |
+
"total_flos": 1.2564599871773491e+17,
|
| 38 |
+
"train_loss": 1.2537303696030295,
|
| 39 |
+
"train_runtime": 320.3475,
|
| 40 |
+
"train_samples_per_second": 10.857,
|
| 41 |
+
"train_steps_per_second": 1.355
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"max_steps": 434,
|
| 45 |
+
"num_train_epochs": 1,
|
| 46 |
+
"total_flos": 1.2564599871773491e+17,
|
| 47 |
+
"trial_name": null,
|
| 48 |
+
"trial_params": null
|
| 49 |
+
}
|