End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.6767448105720579,
|
| 4 |
+
"eval_loss": 1.5883047580718994,
|
| 5 |
+
"eval_runtime": 2254.3702,
|
| 6 |
+
"eval_samples": 565200,
|
| 7 |
+
"eval_samples_per_second": 250.713,
|
| 8 |
+
"eval_steps_per_second": 31.339,
|
| 9 |
+
"perplexity": 4.8954429298660465,
|
| 10 |
+
"train_loss": 1.602422630448058,
|
| 11 |
+
"train_runtime": 56205.4133,
|
| 12 |
+
"train_samples": 2067465,
|
| 13 |
+
"train_samples_per_second": 110.352,
|
| 14 |
+
"train_steps_per_second": 0.014
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.6767448105720579,
|
| 4 |
+
"eval_loss": 1.5883047580718994,
|
| 5 |
+
"eval_runtime": 2254.3702,
|
| 6 |
+
"eval_samples": 565200,
|
| 7 |
+
"eval_samples_per_second": 250.713,
|
| 8 |
+
"eval_steps_per_second": 31.339,
|
| 9 |
+
"perplexity": 4.8954429298660465
|
| 10 |
+
}
|
runs/Jun23_19-17-32_r5u11n1.puma.hpc.arizona.edu/events.out.tfevents.1656095686.r5u11n1.puma.hpc.arizona.edu.95801.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:462db89360d19d32691adcbf663cbbd5a8fcb38f74c5f4f60e4daac82885419c
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.602422630448058,
|
| 4 |
+
"train_runtime": 56205.4133,
|
| 5 |
+
"train_samples": 2067465,
|
| 6 |
+
"train_samples_per_second": 110.352,
|
| 7 |
+
"train_steps_per_second": 0.014
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9983206544030585,
|
| 5 |
+
"global_step": 774,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.94,
|
| 12 |
+
"learning_rate": 0.00010620155038759689,
|
| 13 |
+
"loss": 1.6514,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 3.0,
|
| 18 |
+
"step": 774,
|
| 19 |
+
"total_flos": 4.195821253201335e+17,
|
| 20 |
+
"train_loss": 1.602422630448058,
|
| 21 |
+
"train_runtime": 56205.4133,
|
| 22 |
+
"train_samples_per_second": 110.352,
|
| 23 |
+
"train_steps_per_second": 0.014
|
| 24 |
+
}
|
| 25 |
+
],
|
| 26 |
+
"max_steps": 774,
|
| 27 |
+
"num_train_epochs": 3,
|
| 28 |
+
"total_flos": 4.195821253201335e+17,
|
| 29 |
+
"trial_name": null,
|
| 30 |
+
"trial_params": null
|
| 31 |
+
}
|