End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +31 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.9761986998923713,
|
| 4 |
+
"train_runtime": 1278.1344,
|
| 5 |
+
"train_samples": 11044,
|
| 6 |
+
"train_samples_per_second": 25.922,
|
| 7 |
+
"train_steps_per_second": 0.406
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 2.9761986998923713,
|
| 4 |
+
"train_runtime": 1278.1344,
|
| 5 |
+
"train_samples": 11044,
|
| 6 |
+
"train_samples_per_second": 25.922,
|
| 7 |
+
"train_steps_per_second": 0.406
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 519,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.89,
|
| 12 |
+
"learning_rate": 1.8304431599229288e-06,
|
| 13 |
+
"loss": 2.984,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 3.0,
|
| 18 |
+
"step": 519,
|
| 19 |
+
"total_flos": 7.945359287176397e+16,
|
| 20 |
+
"train_loss": 2.9761986998923713,
|
| 21 |
+
"train_runtime": 1278.1344,
|
| 22 |
+
"train_samples_per_second": 25.922,
|
| 23 |
+
"train_steps_per_second": 0.406
|
| 24 |
+
}
|
| 25 |
+
],
|
| 26 |
+
"max_steps": 519,
|
| 27 |
+
"num_train_epochs": 3,
|
| 28 |
+
"total_flos": 7.945359287176397e+16,
|
| 29 |
+
"trial_name": null,
|
| 30 |
+
"trial_params": null
|
| 31 |
+
}
|