End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +37 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"train_loss": 2.174733916406809,
|
| 4 |
+
"train_runtime": 8756.4326,
|
| 5 |
+
"train_samples": 279992,
|
| 6 |
+
"train_samples_per_second": 191.853,
|
| 7 |
+
"train_steps_per_second": 0.16
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"train_loss": 2.174733916406809,
|
| 4 |
+
"train_runtime": 8756.4326,
|
| 5 |
+
"train_samples": 279992,
|
| 6 |
+
"train_samples_per_second": 191.853,
|
| 7 |
+
"train_steps_per_second": 0.16
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.9983931440814136,
|
| 5 |
+
"global_step": 1398,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.15,
|
| 12 |
+
"learning_rate": 6.42346208869814e-06,
|
| 13 |
+
"loss": 2.369,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 4.29,
|
| 18 |
+
"learning_rate": 2.8469241773962807e-06,
|
| 19 |
+
"loss": 2.0863,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 6.0,
|
| 24 |
+
"step": 1398,
|
| 25 |
+
"total_flos": 3.490577523475661e+17,
|
| 26 |
+
"train_loss": 2.174733916406809,
|
| 27 |
+
"train_runtime": 8756.4326,
|
| 28 |
+
"train_samples_per_second": 191.853,
|
| 29 |
+
"train_steps_per_second": 0.16
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"max_steps": 1398,
|
| 33 |
+
"num_train_epochs": 6,
|
| 34 |
+
"total_flos": 3.490577523475661e+17,
|
| 35 |
+
"trial_name": null,
|
| 36 |
+
"trial_params": null
|
| 37 |
+
}
|