End of training
Browse files- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1135 -0
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.673551838186588e+17,
|
| 4 |
+
"train_loss": 1.320114940725347,
|
| 5 |
+
"train_runtime": 11616.0305,
|
| 6 |
+
"train_samples": 5953,
|
| 7 |
+
"train_samples_per_second": 0.512,
|
| 8 |
+
"train_steps_per_second": 0.064
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.673551838186588e+17,
|
| 4 |
+
"train_loss": 1.320114940725347,
|
| 5 |
+
"train_runtime": 11616.0305,
|
| 6 |
+
"train_samples": 5953,
|
| 7 |
+
"train_samples_per_second": 0.512,
|
| 8 |
+
"train_steps_per_second": 0.064
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9993284083277367,
|
| 5 |
+
"global_step": 744,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 9.865591397849462e-05,
|
| 13 |
+
"loss": 1.8106,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"eval_accuracy": 0.19744795560836792,
|
| 19 |
+
"eval_loss": 1.7615934610366821,
|
| 20 |
+
"eval_runtime": 134.0063,
|
| 21 |
+
"eval_samples_per_second": 11.111,
|
| 22 |
+
"eval_steps_per_second": 2.783,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 9.731182795698925e-05,
|
| 28 |
+
"loss": 1.7268,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"eval_accuracy": 0.2525184750556946,
|
| 34 |
+
"eval_loss": 1.7187447547912598,
|
| 35 |
+
"eval_runtime": 145.4077,
|
| 36 |
+
"eval_samples_per_second": 10.24,
|
| 37 |
+
"eval_steps_per_second": 2.565,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"learning_rate": 9.596774193548387e-05,
|
| 43 |
+
"loss": 1.7269,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04,
|
| 48 |
+
"eval_accuracy": 0.309603750705719,
|
| 49 |
+
"eval_loss": 1.6442092657089233,
|
| 50 |
+
"eval_runtime": 144.9066,
|
| 51 |
+
"eval_samples_per_second": 10.276,
|
| 52 |
+
"eval_steps_per_second": 2.574,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.05,
|
| 57 |
+
"learning_rate": 9.46236559139785e-05,
|
| 58 |
+
"loss": 1.7086,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.05,
|
| 63 |
+
"eval_accuracy": 0.33378106355667114,
|
| 64 |
+
"eval_loss": 1.583362340927124,
|
| 65 |
+
"eval_runtime": 135.7155,
|
| 66 |
+
"eval_samples_per_second": 10.971,
|
| 67 |
+
"eval_steps_per_second": 2.748,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.07,
|
| 72 |
+
"learning_rate": 9.327956989247312e-05,
|
| 73 |
+
"loss": 1.6983,
|
| 74 |
+
"step": 50
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.07,
|
| 78 |
+
"eval_accuracy": 0.35997313261032104,
|
| 79 |
+
"eval_loss": 1.6194798946380615,
|
| 80 |
+
"eval_runtime": 135.5719,
|
| 81 |
+
"eval_samples_per_second": 10.983,
|
| 82 |
+
"eval_steps_per_second": 2.751,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.08,
|
| 87 |
+
"learning_rate": 9.193548387096774e-05,
|
| 88 |
+
"loss": 1.5845,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.08,
|
| 93 |
+
"eval_accuracy": 0.34184014797210693,
|
| 94 |
+
"eval_loss": 1.575337290763855,
|
| 95 |
+
"eval_runtime": 135.8178,
|
| 96 |
+
"eval_samples_per_second": 10.963,
|
| 97 |
+
"eval_steps_per_second": 2.746,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.09,
|
| 102 |
+
"learning_rate": 9.059139784946237e-05,
|
| 103 |
+
"loss": 1.5744,
|
| 104 |
+
"step": 70
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.09,
|
| 108 |
+
"eval_accuracy": 0.3707185983657837,
|
| 109 |
+
"eval_loss": 1.5669182538986206,
|
| 110 |
+
"eval_runtime": 135.433,
|
| 111 |
+
"eval_samples_per_second": 10.994,
|
| 112 |
+
"eval_steps_per_second": 2.754,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.11,
|
| 117 |
+
"learning_rate": 8.924731182795699e-05,
|
| 118 |
+
"loss": 1.5915,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.11,
|
| 123 |
+
"eval_accuracy": 0.3754197359085083,
|
| 124 |
+
"eval_loss": 1.5411657094955444,
|
| 125 |
+
"eval_runtime": 135.3362,
|
| 126 |
+
"eval_samples_per_second": 11.002,
|
| 127 |
+
"eval_steps_per_second": 2.756,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.12,
|
| 132 |
+
"learning_rate": 8.790322580645162e-05,
|
| 133 |
+
"loss": 1.5105,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.12,
|
| 138 |
+
"eval_accuracy": 0.2612491548061371,
|
| 139 |
+
"eval_loss": 2.0037343502044678,
|
| 140 |
+
"eval_runtime": 135.2385,
|
| 141 |
+
"eval_samples_per_second": 11.01,
|
| 142 |
+
"eval_steps_per_second": 2.758,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.13,
|
| 147 |
+
"learning_rate": 8.655913978494624e-05,
|
| 148 |
+
"loss": 1.4689,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.13,
|
| 153 |
+
"eval_accuracy": 0.3626595139503479,
|
| 154 |
+
"eval_loss": 1.5439659357070923,
|
| 155 |
+
"eval_runtime": 135.2487,
|
| 156 |
+
"eval_samples_per_second": 11.009,
|
| 157 |
+
"eval_steps_per_second": 2.758,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.15,
|
| 162 |
+
"learning_rate": 8.521505376344086e-05,
|
| 163 |
+
"loss": 1.527,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.15,
|
| 168 |
+
"eval_accuracy": 0.38616520166397095,
|
| 169 |
+
"eval_loss": 1.540026068687439,
|
| 170 |
+
"eval_runtime": 135.6976,
|
| 171 |
+
"eval_samples_per_second": 10.973,
|
| 172 |
+
"eval_steps_per_second": 2.749,
|
| 173 |
+
"step": 110
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.16,
|
| 177 |
+
"learning_rate": 8.387096774193549e-05,
|
| 178 |
+
"loss": 1.6481,
|
| 179 |
+
"step": 120
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.16,
|
| 183 |
+
"eval_accuracy": 0.32975152134895325,
|
| 184 |
+
"eval_loss": 1.6678365468978882,
|
| 185 |
+
"eval_runtime": 135.8659,
|
| 186 |
+
"eval_samples_per_second": 10.959,
|
| 187 |
+
"eval_steps_per_second": 2.745,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.17,
|
| 192 |
+
"learning_rate": 8.252688172043011e-05,
|
| 193 |
+
"loss": 1.7504,
|
| 194 |
+
"step": 130
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.17,
|
| 198 |
+
"eval_accuracy": 0.29952988028526306,
|
| 199 |
+
"eval_loss": 1.6077724695205688,
|
| 200 |
+
"eval_runtime": 135.8936,
|
| 201 |
+
"eval_samples_per_second": 10.957,
|
| 202 |
+
"eval_steps_per_second": 2.745,
|
| 203 |
+
"step": 130
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.19,
|
| 207 |
+
"learning_rate": 8.118279569892473e-05,
|
| 208 |
+
"loss": 1.3748,
|
| 209 |
+
"step": 140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.19,
|
| 213 |
+
"eval_accuracy": 0.32505038380622864,
|
| 214 |
+
"eval_loss": 1.5750231742858887,
|
| 215 |
+
"eval_runtime": 135.7593,
|
| 216 |
+
"eval_samples_per_second": 10.968,
|
| 217 |
+
"eval_steps_per_second": 2.748,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.2,
|
| 222 |
+
"learning_rate": 7.983870967741936e-05,
|
| 223 |
+
"loss": 1.6417,
|
| 224 |
+
"step": 150
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.2,
|
| 228 |
+
"eval_accuracy": 0.25990596413612366,
|
| 229 |
+
"eval_loss": 1.7033889293670654,
|
| 230 |
+
"eval_runtime": 140.3888,
|
| 231 |
+
"eval_samples_per_second": 10.606,
|
| 232 |
+
"eval_steps_per_second": 2.657,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.21,
|
| 237 |
+
"learning_rate": 7.849462365591398e-05,
|
| 238 |
+
"loss": 1.6146,
|
| 239 |
+
"step": 160
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.21,
|
| 243 |
+
"eval_accuracy": 0.35191404819488525,
|
| 244 |
+
"eval_loss": 1.6161645650863647,
|
| 245 |
+
"eval_runtime": 136.7498,
|
| 246 |
+
"eval_samples_per_second": 10.889,
|
| 247 |
+
"eval_steps_per_second": 2.728,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.23,
|
| 252 |
+
"learning_rate": 7.715053763440861e-05,
|
| 253 |
+
"loss": 1.4896,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.23,
|
| 258 |
+
"eval_accuracy": 0.37407657504081726,
|
| 259 |
+
"eval_loss": 1.5245014429092407,
|
| 260 |
+
"eval_runtime": 137.1791,
|
| 261 |
+
"eval_samples_per_second": 10.854,
|
| 262 |
+
"eval_steps_per_second": 2.719,
|
| 263 |
+
"step": 170
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.24,
|
| 267 |
+
"learning_rate": 7.580645161290323e-05,
|
| 268 |
+
"loss": 1.4278,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.24,
|
| 273 |
+
"eval_accuracy": 0.24244458973407745,
|
| 274 |
+
"eval_loss": 1.7536966800689697,
|
| 275 |
+
"eval_runtime": 137.1089,
|
| 276 |
+
"eval_samples_per_second": 10.86,
|
| 277 |
+
"eval_steps_per_second": 2.72,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.26,
|
| 282 |
+
"learning_rate": 7.446236559139786e-05,
|
| 283 |
+
"loss": 1.4475,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.26,
|
| 288 |
+
"eval_accuracy": 0.3881799876689911,
|
| 289 |
+
"eval_loss": 1.4769032001495361,
|
| 290 |
+
"eval_runtime": 136.7534,
|
| 291 |
+
"eval_samples_per_second": 10.888,
|
| 292 |
+
"eval_steps_per_second": 2.728,
|
| 293 |
+
"step": 190
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.27,
|
| 297 |
+
"learning_rate": 7.311827956989248e-05,
|
| 298 |
+
"loss": 1.5416,
|
| 299 |
+
"step": 200
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.27,
|
| 303 |
+
"eval_accuracy": 0.39489591121673584,
|
| 304 |
+
"eval_loss": 1.4772460460662842,
|
| 305 |
+
"eval_runtime": 137.0691,
|
| 306 |
+
"eval_samples_per_second": 10.863,
|
| 307 |
+
"eval_steps_per_second": 2.721,
|
| 308 |
+
"step": 200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.28,
|
| 312 |
+
"learning_rate": 7.177419354838711e-05,
|
| 313 |
+
"loss": 1.5997,
|
| 314 |
+
"step": 210
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.28,
|
| 318 |
+
"eval_accuracy": 0.4278039038181305,
|
| 319 |
+
"eval_loss": 1.4428460597991943,
|
| 320 |
+
"eval_runtime": 137.003,
|
| 321 |
+
"eval_samples_per_second": 10.868,
|
| 322 |
+
"eval_steps_per_second": 2.723,
|
| 323 |
+
"step": 210
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.3,
|
| 327 |
+
"learning_rate": 7.043010752688173e-05,
|
| 328 |
+
"loss": 1.4337,
|
| 329 |
+
"step": 220
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.3,
|
| 333 |
+
"eval_accuracy": 0.41235730051994324,
|
| 334 |
+
"eval_loss": 1.435219645500183,
|
| 335 |
+
"eval_runtime": 137.007,
|
| 336 |
+
"eval_samples_per_second": 10.868,
|
| 337 |
+
"eval_steps_per_second": 2.722,
|
| 338 |
+
"step": 220
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.31,
|
| 342 |
+
"learning_rate": 6.908602150537635e-05,
|
| 343 |
+
"loss": 1.415,
|
| 344 |
+
"step": 230
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.31,
|
| 348 |
+
"eval_accuracy": 0.4157152473926544,
|
| 349 |
+
"eval_loss": 1.4404770135879517,
|
| 350 |
+
"eval_runtime": 137.0627,
|
| 351 |
+
"eval_samples_per_second": 10.864,
|
| 352 |
+
"eval_steps_per_second": 2.721,
|
| 353 |
+
"step": 230
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.32,
|
| 357 |
+
"learning_rate": 6.774193548387096e-05,
|
| 358 |
+
"loss": 1.5196,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.32,
|
| 363 |
+
"eval_accuracy": 0.40429818630218506,
|
| 364 |
+
"eval_loss": 1.4196510314941406,
|
| 365 |
+
"eval_runtime": 136.8253,
|
| 366 |
+
"eval_samples_per_second": 10.882,
|
| 367 |
+
"eval_steps_per_second": 2.726,
|
| 368 |
+
"step": 240
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.34,
|
| 372 |
+
"learning_rate": 6.63978494623656e-05,
|
| 373 |
+
"loss": 1.3866,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.34,
|
| 378 |
+
"eval_accuracy": 0.37340497970581055,
|
| 379 |
+
"eval_loss": 1.524086833000183,
|
| 380 |
+
"eval_runtime": 137.3465,
|
| 381 |
+
"eval_samples_per_second": 10.841,
|
| 382 |
+
"eval_steps_per_second": 2.716,
|
| 383 |
+
"step": 250
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.35,
|
| 387 |
+
"learning_rate": 6.505376344086021e-05,
|
| 388 |
+
"loss": 1.3041,
|
| 389 |
+
"step": 260
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.35,
|
| 393 |
+
"eval_accuracy": 0.40429818630218506,
|
| 394 |
+
"eval_loss": 1.5703184604644775,
|
| 395 |
+
"eval_runtime": 136.9308,
|
| 396 |
+
"eval_samples_per_second": 10.874,
|
| 397 |
+
"eval_steps_per_second": 2.724,
|
| 398 |
+
"step": 260
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.36,
|
| 402 |
+
"learning_rate": 6.370967741935485e-05,
|
| 403 |
+
"loss": 1.3618,
|
| 404 |
+
"step": 270
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.36,
|
| 408 |
+
"eval_accuracy": 0.4284754991531372,
|
| 409 |
+
"eval_loss": 1.3963350057601929,
|
| 410 |
+
"eval_runtime": 136.0816,
|
| 411 |
+
"eval_samples_per_second": 10.942,
|
| 412 |
+
"eval_steps_per_second": 2.741,
|
| 413 |
+
"step": 270
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.38,
|
| 417 |
+
"learning_rate": 6.236559139784946e-05,
|
| 418 |
+
"loss": 1.3293,
|
| 419 |
+
"step": 280
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.38,
|
| 423 |
+
"eval_accuracy": 0.4506380259990692,
|
| 424 |
+
"eval_loss": 1.3478150367736816,
|
| 425 |
+
"eval_runtime": 135.9673,
|
| 426 |
+
"eval_samples_per_second": 10.951,
|
| 427 |
+
"eval_steps_per_second": 2.743,
|
| 428 |
+
"step": 280
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.39,
|
| 432 |
+
"learning_rate": 6.102150537634409e-05,
|
| 433 |
+
"loss": 1.2215,
|
| 434 |
+
"step": 290
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.39,
|
| 438 |
+
"eval_accuracy": 0.3841504454612732,
|
| 439 |
+
"eval_loss": 1.5994166135787964,
|
| 440 |
+
"eval_runtime": 136.1871,
|
| 441 |
+
"eval_samples_per_second": 10.933,
|
| 442 |
+
"eval_steps_per_second": 2.739,
|
| 443 |
+
"step": 290
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.4,
|
| 447 |
+
"learning_rate": 5.9677419354838715e-05,
|
| 448 |
+
"loss": 1.6618,
|
| 449 |
+
"step": 300
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.4,
|
| 453 |
+
"eval_accuracy": 0.2276695817708969,
|
| 454 |
+
"eval_loss": 1.7750705480575562,
|
| 455 |
+
"eval_runtime": 136.1639,
|
| 456 |
+
"eval_samples_per_second": 10.935,
|
| 457 |
+
"eval_steps_per_second": 2.739,
|
| 458 |
+
"step": 300
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.42,
|
| 462 |
+
"learning_rate": 5.8467741935483876e-05,
|
| 463 |
+
"loss": 1.5349,
|
| 464 |
+
"step": 310
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.42,
|
| 468 |
+
"eval_accuracy": 0.40362659096717834,
|
| 469 |
+
"eval_loss": 1.6090513467788696,
|
| 470 |
+
"eval_runtime": 136.1264,
|
| 471 |
+
"eval_samples_per_second": 10.938,
|
| 472 |
+
"eval_steps_per_second": 2.74,
|
| 473 |
+
"step": 310
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.43,
|
| 477 |
+
"learning_rate": 5.71236559139785e-05,
|
| 478 |
+
"loss": 1.4037,
|
| 479 |
+
"step": 320
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.43,
|
| 483 |
+
"eval_accuracy": 0.4445936977863312,
|
| 484 |
+
"eval_loss": 1.4741053581237793,
|
| 485 |
+
"eval_runtime": 136.0584,
|
| 486 |
+
"eval_samples_per_second": 10.944,
|
| 487 |
+
"eval_steps_per_second": 2.741,
|
| 488 |
+
"step": 320
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.44,
|
| 492 |
+
"learning_rate": 5.577956989247311e-05,
|
| 493 |
+
"loss": 1.4844,
|
| 494 |
+
"step": 330
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.44,
|
| 498 |
+
"eval_accuracy": 0.4398925304412842,
|
| 499 |
+
"eval_loss": 1.4170390367507935,
|
| 500 |
+
"eval_runtime": 136.1183,
|
| 501 |
+
"eval_samples_per_second": 10.939,
|
| 502 |
+
"eval_steps_per_second": 2.74,
|
| 503 |
+
"step": 330
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.46,
|
| 507 |
+
"learning_rate": 5.443548387096774e-05,
|
| 508 |
+
"loss": 1.2806,
|
| 509 |
+
"step": 340
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.46,
|
| 513 |
+
"eval_accuracy": 0.5050369501113892,
|
| 514 |
+
"eval_loss": 1.2886841297149658,
|
| 515 |
+
"eval_runtime": 136.1309,
|
| 516 |
+
"eval_samples_per_second": 10.938,
|
| 517 |
+
"eval_steps_per_second": 2.74,
|
| 518 |
+
"step": 340
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.47,
|
| 522 |
+
"learning_rate": 5.309139784946236e-05,
|
| 523 |
+
"loss": 1.3818,
|
| 524 |
+
"step": 350
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.47,
|
| 528 |
+
"eval_accuracy": 0.501679003238678,
|
| 529 |
+
"eval_loss": 1.2668293714523315,
|
| 530 |
+
"eval_runtime": 135.9509,
|
| 531 |
+
"eval_samples_per_second": 10.952,
|
| 532 |
+
"eval_steps_per_second": 2.744,
|
| 533 |
+
"step": 350
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.48,
|
| 537 |
+
"learning_rate": 5.174731182795699e-05,
|
| 538 |
+
"loss": 1.3491,
|
| 539 |
+
"step": 360
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.48,
|
| 543 |
+
"eval_accuracy": 0.4593687057495117,
|
| 544 |
+
"eval_loss": 1.4720617532730103,
|
| 545 |
+
"eval_runtime": 136.1018,
|
| 546 |
+
"eval_samples_per_second": 10.94,
|
| 547 |
+
"eval_steps_per_second": 2.741,
|
| 548 |
+
"step": 360
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.5,
|
| 552 |
+
"learning_rate": 5.040322580645161e-05,
|
| 553 |
+
"loss": 1.2347,
|
| 554 |
+
"step": 370
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.5,
|
| 558 |
+
"eval_accuracy": 0.5245131254196167,
|
| 559 |
+
"eval_loss": 1.2187544107437134,
|
| 560 |
+
"eval_runtime": 136.1642,
|
| 561 |
+
"eval_samples_per_second": 10.935,
|
| 562 |
+
"eval_steps_per_second": 2.739,
|
| 563 |
+
"step": 370
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.51,
|
| 567 |
+
"learning_rate": 4.905913978494624e-05,
|
| 568 |
+
"loss": 1.2182,
|
| 569 |
+
"step": 380
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.51,
|
| 573 |
+
"eval_accuracy": 0.45668232440948486,
|
| 574 |
+
"eval_loss": 1.3813459873199463,
|
| 575 |
+
"eval_runtime": 136.1044,
|
| 576 |
+
"eval_samples_per_second": 10.94,
|
| 577 |
+
"eval_steps_per_second": 2.741,
|
| 578 |
+
"step": 380
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.52,
|
| 582 |
+
"learning_rate": 4.771505376344086e-05,
|
| 583 |
+
"loss": 1.2513,
|
| 584 |
+
"step": 390
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.52,
|
| 588 |
+
"eval_accuracy": 0.5204835534095764,
|
| 589 |
+
"eval_loss": 1.2110750675201416,
|
| 590 |
+
"eval_runtime": 136.1563,
|
| 591 |
+
"eval_samples_per_second": 10.936,
|
| 592 |
+
"eval_steps_per_second": 2.739,
|
| 593 |
+
"step": 390
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.54,
|
| 597 |
+
"learning_rate": 4.637096774193548e-05,
|
| 598 |
+
"loss": 1.2447,
|
| 599 |
+
"step": 400
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.54,
|
| 603 |
+
"eval_accuracy": 0.546004056930542,
|
| 604 |
+
"eval_loss": 1.2230509519577026,
|
| 605 |
+
"eval_runtime": 136.1489,
|
| 606 |
+
"eval_samples_per_second": 10.937,
|
| 607 |
+
"eval_steps_per_second": 2.74,
|
| 608 |
+
"step": 400
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.55,
|
| 612 |
+
"learning_rate": 4.516129032258064e-05,
|
| 613 |
+
"loss": 1.038,
|
| 614 |
+
"step": 410
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.55,
|
| 618 |
+
"eval_accuracy": 0.5372733473777771,
|
| 619 |
+
"eval_loss": 1.2562698125839233,
|
| 620 |
+
"eval_runtime": 136.2823,
|
| 621 |
+
"eval_samples_per_second": 10.926,
|
| 622 |
+
"eval_steps_per_second": 2.737,
|
| 623 |
+
"step": 410
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.56,
|
| 627 |
+
"learning_rate": 4.381720430107527e-05,
|
| 628 |
+
"loss": 1.2409,
|
| 629 |
+
"step": 420
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.56,
|
| 633 |
+
"eval_accuracy": 0.4936198890209198,
|
| 634 |
+
"eval_loss": 1.344766616821289,
|
| 635 |
+
"eval_runtime": 136.1885,
|
| 636 |
+
"eval_samples_per_second": 10.933,
|
| 637 |
+
"eval_steps_per_second": 2.739,
|
| 638 |
+
"step": 420
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.58,
|
| 642 |
+
"learning_rate": 4.247311827956989e-05,
|
| 643 |
+
"loss": 1.2279,
|
| 644 |
+
"step": 430
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.58,
|
| 648 |
+
"eval_accuracy": 0.5486903786659241,
|
| 649 |
+
"eval_loss": 1.1971595287322998,
|
| 650 |
+
"eval_runtime": 136.416,
|
| 651 |
+
"eval_samples_per_second": 10.915,
|
| 652 |
+
"eval_steps_per_second": 2.734,
|
| 653 |
+
"step": 430
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.59,
|
| 657 |
+
"learning_rate": 4.112903225806452e-05,
|
| 658 |
+
"loss": 1.3256,
|
| 659 |
+
"step": 440
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.59,
|
| 663 |
+
"eval_accuracy": 0.5742108821868896,
|
| 664 |
+
"eval_loss": 1.1706324815750122,
|
| 665 |
+
"eval_runtime": 136.371,
|
| 666 |
+
"eval_samples_per_second": 10.919,
|
| 667 |
+
"eval_steps_per_second": 2.735,
|
| 668 |
+
"step": 440
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.6,
|
| 672 |
+
"learning_rate": 3.978494623655914e-05,
|
| 673 |
+
"loss": 1.2866,
|
| 674 |
+
"step": 450
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6,
|
| 678 |
+
"eval_accuracy": 0.5003358125686646,
|
| 679 |
+
"eval_loss": 1.309117078781128,
|
| 680 |
+
"eval_runtime": 136.1709,
|
| 681 |
+
"eval_samples_per_second": 10.935,
|
| 682 |
+
"eval_steps_per_second": 2.739,
|
| 683 |
+
"step": 450
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.62,
|
| 687 |
+
"learning_rate": 3.844086021505376e-05,
|
| 688 |
+
"loss": 1.0574,
|
| 689 |
+
"step": 460
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.62,
|
| 693 |
+
"eval_accuracy": 0.5500335693359375,
|
| 694 |
+
"eval_loss": 1.2074663639068604,
|
| 695 |
+
"eval_runtime": 136.5936,
|
| 696 |
+
"eval_samples_per_second": 10.901,
|
| 697 |
+
"eval_steps_per_second": 2.731,
|
| 698 |
+
"step": 460
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.63,
|
| 702 |
+
"learning_rate": 3.7096774193548386e-05,
|
| 703 |
+
"loss": 1.2744,
|
| 704 |
+
"step": 470
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.63,
|
| 708 |
+
"eval_accuracy": 0.5171256065368652,
|
| 709 |
+
"eval_loss": 1.2830621004104614,
|
| 710 |
+
"eval_runtime": 136.8418,
|
| 711 |
+
"eval_samples_per_second": 10.881,
|
| 712 |
+
"eval_steps_per_second": 2.726,
|
| 713 |
+
"step": 470
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.64,
|
| 717 |
+
"learning_rate": 3.575268817204301e-05,
|
| 718 |
+
"loss": 1.0836,
|
| 719 |
+
"step": 480
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.64,
|
| 723 |
+
"eval_accuracy": 0.5607790350914001,
|
| 724 |
+
"eval_loss": 1.1768107414245605,
|
| 725 |
+
"eval_runtime": 136.4906,
|
| 726 |
+
"eval_samples_per_second": 10.909,
|
| 727 |
+
"eval_steps_per_second": 2.733,
|
| 728 |
+
"step": 480
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.66,
|
| 732 |
+
"learning_rate": 3.4408602150537636e-05,
|
| 733 |
+
"loss": 1.135,
|
| 734 |
+
"step": 490
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.66,
|
| 738 |
+
"eval_accuracy": 0.5775688290596008,
|
| 739 |
+
"eval_loss": 1.1407707929611206,
|
| 740 |
+
"eval_runtime": 136.5812,
|
| 741 |
+
"eval_samples_per_second": 10.902,
|
| 742 |
+
"eval_steps_per_second": 2.731,
|
| 743 |
+
"step": 490
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.67,
|
| 747 |
+
"learning_rate": 3.306451612903226e-05,
|
| 748 |
+
"loss": 1.1303,
|
| 749 |
+
"step": 500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.67,
|
| 753 |
+
"eval_accuracy": 0.5540631413459778,
|
| 754 |
+
"eval_loss": 1.2319557666778564,
|
| 755 |
+
"eval_runtime": 136.447,
|
| 756 |
+
"eval_samples_per_second": 10.913,
|
| 757 |
+
"eval_steps_per_second": 2.734,
|
| 758 |
+
"step": 500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.69,
|
| 762 |
+
"learning_rate": 3.172043010752688e-05,
|
| 763 |
+
"loss": 1.2068,
|
| 764 |
+
"step": 510
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.69,
|
| 768 |
+
"eval_accuracy": 0.5795835852622986,
|
| 769 |
+
"eval_loss": 1.1379237174987793,
|
| 770 |
+
"eval_runtime": 139.7377,
|
| 771 |
+
"eval_samples_per_second": 10.656,
|
| 772 |
+
"eval_steps_per_second": 2.669,
|
| 773 |
+
"step": 510
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.7,
|
| 777 |
+
"learning_rate": 3.0376344086021508e-05,
|
| 778 |
+
"loss": 1.1347,
|
| 779 |
+
"step": 520
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.7,
|
| 783 |
+
"eval_accuracy": 0.5896574854850769,
|
| 784 |
+
"eval_loss": 1.112443447113037,
|
| 785 |
+
"eval_runtime": 135.8322,
|
| 786 |
+
"eval_samples_per_second": 10.962,
|
| 787 |
+
"eval_steps_per_second": 2.746,
|
| 788 |
+
"step": 520
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.71,
|
| 792 |
+
"learning_rate": 2.9032258064516133e-05,
|
| 793 |
+
"loss": 1.1846,
|
| 794 |
+
"step": 530
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.71,
|
| 798 |
+
"eval_accuracy": 0.5802552103996277,
|
| 799 |
+
"eval_loss": 1.1337865591049194,
|
| 800 |
+
"eval_runtime": 136.0081,
|
| 801 |
+
"eval_samples_per_second": 10.948,
|
| 802 |
+
"eval_steps_per_second": 2.742,
|
| 803 |
+
"step": 530
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.73,
|
| 807 |
+
"learning_rate": 2.768817204301075e-05,
|
| 808 |
+
"loss": 1.2409,
|
| 809 |
+
"step": 540
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.73,
|
| 813 |
+
"eval_accuracy": 0.5789120197296143,
|
| 814 |
+
"eval_loss": 1.1259396076202393,
|
| 815 |
+
"eval_runtime": 136.2241,
|
| 816 |
+
"eval_samples_per_second": 10.931,
|
| 817 |
+
"eval_steps_per_second": 2.738,
|
| 818 |
+
"step": 540
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.74,
|
| 822 |
+
"learning_rate": 2.6344086021505376e-05,
|
| 823 |
+
"loss": 1.0664,
|
| 824 |
+
"step": 550
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.74,
|
| 828 |
+
"eval_accuracy": 0.6037608981132507,
|
| 829 |
+
"eval_loss": 1.065294861793518,
|
| 830 |
+
"eval_runtime": 136.1781,
|
| 831 |
+
"eval_samples_per_second": 10.934,
|
| 832 |
+
"eval_steps_per_second": 2.739,
|
| 833 |
+
"step": 550
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.75,
|
| 837 |
+
"learning_rate": 2.5e-05,
|
| 838 |
+
"loss": 1.1637,
|
| 839 |
+
"step": 560
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.75,
|
| 843 |
+
"eval_accuracy": 0.5977165699005127,
|
| 844 |
+
"eval_loss": 1.0549540519714355,
|
| 845 |
+
"eval_runtime": 135.9124,
|
| 846 |
+
"eval_samples_per_second": 10.956,
|
| 847 |
+
"eval_steps_per_second": 2.744,
|
| 848 |
+
"step": 560
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.77,
|
| 852 |
+
"learning_rate": 2.3655913978494626e-05,
|
| 853 |
+
"loss": 1.0707,
|
| 854 |
+
"step": 570
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.77,
|
| 858 |
+
"eval_accuracy": 0.5715245008468628,
|
| 859 |
+
"eval_loss": 1.0996488332748413,
|
| 860 |
+
"eval_runtime": 136.1326,
|
| 861 |
+
"eval_samples_per_second": 10.938,
|
| 862 |
+
"eval_steps_per_second": 2.74,
|
| 863 |
+
"step": 570
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.78,
|
| 867 |
+
"learning_rate": 2.2311827956989248e-05,
|
| 868 |
+
"loss": 1.2258,
|
| 869 |
+
"step": 580
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.78,
|
| 873 |
+
"eval_accuracy": 0.5977165699005127,
|
| 874 |
+
"eval_loss": 1.080415964126587,
|
| 875 |
+
"eval_runtime": 135.8671,
|
| 876 |
+
"eval_samples_per_second": 10.959,
|
| 877 |
+
"eval_steps_per_second": 2.745,
|
| 878 |
+
"step": 580
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.79,
|
| 882 |
+
"learning_rate": 2.0967741935483873e-05,
|
| 883 |
+
"loss": 0.9256,
|
| 884 |
+
"step": 590
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.79,
|
| 888 |
+
"eval_accuracy": 0.580926775932312,
|
| 889 |
+
"eval_loss": 1.1501046419143677,
|
| 890 |
+
"eval_runtime": 135.8439,
|
| 891 |
+
"eval_samples_per_second": 10.961,
|
| 892 |
+
"eval_steps_per_second": 2.746,
|
| 893 |
+
"step": 590
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.81,
|
| 897 |
+
"learning_rate": 1.9623655913978494e-05,
|
| 898 |
+
"loss": 1.1542,
|
| 899 |
+
"step": 600
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.81,
|
| 903 |
+
"eval_accuracy": 0.5957018136978149,
|
| 904 |
+
"eval_loss": 1.1089370250701904,
|
| 905 |
+
"eval_runtime": 137.3702,
|
| 906 |
+
"eval_samples_per_second": 10.839,
|
| 907 |
+
"eval_steps_per_second": 2.715,
|
| 908 |
+
"step": 600
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.82,
|
| 912 |
+
"learning_rate": 1.827956989247312e-05,
|
| 913 |
+
"loss": 1.3931,
|
| 914 |
+
"step": 610
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.82,
|
| 918 |
+
"eval_accuracy": 0.5856279134750366,
|
| 919 |
+
"eval_loss": 1.138110876083374,
|
| 920 |
+
"eval_runtime": 135.8089,
|
| 921 |
+
"eval_samples_per_second": 10.964,
|
| 922 |
+
"eval_steps_per_second": 2.747,
|
| 923 |
+
"step": 610
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.83,
|
| 927 |
+
"learning_rate": 1.693548387096774e-05,
|
| 928 |
+
"loss": 1.1117,
|
| 929 |
+
"step": 620
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.83,
|
| 933 |
+
"eval_accuracy": 0.6030893325805664,
|
| 934 |
+
"eval_loss": 1.0933294296264648,
|
| 935 |
+
"eval_runtime": 135.7612,
|
| 936 |
+
"eval_samples_per_second": 10.968,
|
| 937 |
+
"eval_steps_per_second": 2.747,
|
| 938 |
+
"step": 620
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.85,
|
| 942 |
+
"learning_rate": 1.5591397849462366e-05,
|
| 943 |
+
"loss": 1.1433,
|
| 944 |
+
"step": 630
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.85,
|
| 948 |
+
"eval_accuracy": 0.6218938827514648,
|
| 949 |
+
"eval_loss": 1.0175174474716187,
|
| 950 |
+
"eval_runtime": 135.6802,
|
| 951 |
+
"eval_samples_per_second": 10.974,
|
| 952 |
+
"eval_steps_per_second": 2.749,
|
| 953 |
+
"step": 630
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.86,
|
| 957 |
+
"learning_rate": 1.4247311827956991e-05,
|
| 958 |
+
"loss": 1.0325,
|
| 959 |
+
"step": 640
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.86,
|
| 963 |
+
"eval_accuracy": 0.6239086389541626,
|
| 964 |
+
"eval_loss": 0.9885073304176331,
|
| 965 |
+
"eval_runtime": 135.5378,
|
| 966 |
+
"eval_samples_per_second": 10.986,
|
| 967 |
+
"eval_steps_per_second": 2.752,
|
| 968 |
+
"step": 640
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.87,
|
| 972 |
+
"learning_rate": 1.2903225806451613e-05,
|
| 973 |
+
"loss": 1.111,
|
| 974 |
+
"step": 650
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.87,
|
| 978 |
+
"eval_accuracy": 0.6259234547615051,
|
| 979 |
+
"eval_loss": 1.004755973815918,
|
| 980 |
+
"eval_runtime": 135.7521,
|
| 981 |
+
"eval_samples_per_second": 10.969,
|
| 982 |
+
"eval_steps_per_second": 2.748,
|
| 983 |
+
"step": 650
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.89,
|
| 987 |
+
"learning_rate": 1.1559139784946236e-05,
|
| 988 |
+
"loss": 0.8125,
|
| 989 |
+
"step": 660
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.89,
|
| 993 |
+
"eval_accuracy": 0.6165211796760559,
|
| 994 |
+
"eval_loss": 1.0176496505737305,
|
| 995 |
+
"eval_runtime": 135.5622,
|
| 996 |
+
"eval_samples_per_second": 10.984,
|
| 997 |
+
"eval_steps_per_second": 2.752,
|
| 998 |
+
"step": 660
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.9,
|
| 1002 |
+
"learning_rate": 1.0215053763440861e-05,
|
| 1003 |
+
"loss": 1.0414,
|
| 1004 |
+
"step": 670
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.9,
|
| 1008 |
+
"eval_accuracy": 0.6185359358787537,
|
| 1009 |
+
"eval_loss": 1.0289984941482544,
|
| 1010 |
+
"eval_runtime": 135.9417,
|
| 1011 |
+
"eval_samples_per_second": 10.953,
|
| 1012 |
+
"eval_steps_per_second": 2.744,
|
| 1013 |
+
"step": 670
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.91,
|
| 1017 |
+
"learning_rate": 8.870967741935484e-06,
|
| 1018 |
+
"loss": 1.0037,
|
| 1019 |
+
"step": 680
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.91,
|
| 1023 |
+
"eval_accuracy": 0.625251829624176,
|
| 1024 |
+
"eval_loss": 1.0268802642822266,
|
| 1025 |
+
"eval_runtime": 135.7529,
|
| 1026 |
+
"eval_samples_per_second": 10.968,
|
| 1027 |
+
"eval_steps_per_second": 2.748,
|
| 1028 |
+
"step": 680
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.93,
|
| 1032 |
+
"learning_rate": 7.526881720430108e-06,
|
| 1033 |
+
"loss": 0.9406,
|
| 1034 |
+
"step": 690
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.93,
|
| 1038 |
+
"eval_accuracy": 0.6272666454315186,
|
| 1039 |
+
"eval_loss": 1.0300624370574951,
|
| 1040 |
+
"eval_runtime": 137.5757,
|
| 1041 |
+
"eval_samples_per_second": 10.823,
|
| 1042 |
+
"eval_steps_per_second": 2.711,
|
| 1043 |
+
"step": 690
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.94,
|
| 1047 |
+
"learning_rate": 6.182795698924732e-06,
|
| 1048 |
+
"loss": 1.0129,
|
| 1049 |
+
"step": 700
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.94,
|
| 1053 |
+
"eval_accuracy": 0.6326393485069275,
|
| 1054 |
+
"eval_loss": 1.0238244533538818,
|
| 1055 |
+
"eval_runtime": 135.84,
|
| 1056 |
+
"eval_samples_per_second": 10.961,
|
| 1057 |
+
"eval_steps_per_second": 2.746,
|
| 1058 |
+
"step": 700
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.95,
|
| 1062 |
+
"learning_rate": 4.838709677419355e-06,
|
| 1063 |
+
"loss": 1.2213,
|
| 1064 |
+
"step": 710
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.95,
|
| 1068 |
+
"eval_accuracy": 0.6272666454315186,
|
| 1069 |
+
"eval_loss": 1.018078088760376,
|
| 1070 |
+
"eval_runtime": 135.9017,
|
| 1071 |
+
"eval_samples_per_second": 10.956,
|
| 1072 |
+
"eval_steps_per_second": 2.745,
|
| 1073 |
+
"step": 710
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.97,
|
| 1077 |
+
"learning_rate": 3.4946236559139785e-06,
|
| 1078 |
+
"loss": 1.2519,
|
| 1079 |
+
"step": 720
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.97,
|
| 1083 |
+
"eval_accuracy": 0.6265950202941895,
|
| 1084 |
+
"eval_loss": 1.0160512924194336,
|
| 1085 |
+
"eval_runtime": 135.809,
|
| 1086 |
+
"eval_samples_per_second": 10.964,
|
| 1087 |
+
"eval_steps_per_second": 2.747,
|
| 1088 |
+
"step": 720
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.98,
|
| 1092 |
+
"learning_rate": 2.1505376344086023e-06,
|
| 1093 |
+
"loss": 0.9932,
|
| 1094 |
+
"step": 730
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.98,
|
| 1098 |
+
"eval_accuracy": 0.6279382109642029,
|
| 1099 |
+
"eval_loss": 1.0112457275390625,
|
| 1100 |
+
"eval_runtime": 136.0311,
|
| 1101 |
+
"eval_samples_per_second": 10.946,
|
| 1102 |
+
"eval_steps_per_second": 2.742,
|
| 1103 |
+
"step": 730
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.99,
|
| 1107 |
+
"learning_rate": 8.064516129032258e-07,
|
| 1108 |
+
"loss": 1.0135,
|
| 1109 |
+
"step": 740
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.99,
|
| 1113 |
+
"eval_accuracy": 0.6312961578369141,
|
| 1114 |
+
"eval_loss": 1.010461449623108,
|
| 1115 |
+
"eval_runtime": 136.2447,
|
| 1116 |
+
"eval_samples_per_second": 10.929,
|
| 1117 |
+
"eval_steps_per_second": 2.738,
|
| 1118 |
+
"step": 740
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.0,
|
| 1122 |
+
"step": 744,
|
| 1123 |
+
"total_flos": 1.673551838186588e+17,
|
| 1124 |
+
"train_loss": 1.320114940725347,
|
| 1125 |
+
"train_runtime": 11616.0305,
|
| 1126 |
+
"train_samples_per_second": 0.512,
|
| 1127 |
+
"train_steps_per_second": 0.064
|
| 1128 |
+
}
|
| 1129 |
+
],
|
| 1130 |
+
"max_steps": 744,
|
| 1131 |
+
"num_train_epochs": 1,
|
| 1132 |
+
"total_flos": 1.673551838186588e+17,
|
| 1133 |
+
"trial_name": null,
|
| 1134 |
+
"trial_params": null
|
| 1135 |
+
}
|