Commit
•
7e5b987
1
Parent(s):
be97f84
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.7066666666666667,
|
| 4 |
+
"eval_loss": 1.2085484266281128,
|
| 5 |
+
"eval_runtime": 0.1015,
|
| 6 |
+
"eval_samples": 1,
|
| 7 |
+
"eval_samples_per_second": 9.848,
|
| 8 |
+
"eval_steps_per_second": 9.848,
|
| 9 |
+
"perplexity": 3.3486203548209947,
|
| 10 |
+
"train_loss": 1.552238972981771,
|
| 11 |
+
"train_runtime": 328.4713,
|
| 12 |
+
"train_samples": 45,
|
| 13 |
+
"train_samples_per_second": 4.11,
|
| 14 |
+
"train_steps_per_second": 1.096
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.7066666666666667,
|
| 4 |
+
"eval_loss": 1.2085484266281128,
|
| 5 |
+
"eval_runtime": 0.1015,
|
| 6 |
+
"eval_samples": 1,
|
| 7 |
+
"eval_samples_per_second": 9.848,
|
| 8 |
+
"eval_steps_per_second": 9.848,
|
| 9 |
+
"perplexity": 3.3486203548209947
|
| 10 |
+
}
|
runs/Apr24_14-08-06_14523c674822/events.out.tfevents.1682345777.14523c674822.67070.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4be3fcd9f66c0f9b17fb24400f443fd6f2ed38b27c60fba82b7ccf4a6459770b
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"train_loss": 1.552238972981771,
|
| 4 |
+
"train_runtime": 328.4713,
|
| 5 |
+
"train_samples": 45,
|
| 6 |
+
"train_samples_per_second": 4.11,
|
| 7 |
+
"train_steps_per_second": 1.096
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"global_step": 360,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 30.0,
|
| 12 |
+
"step": 360,
|
| 13 |
+
"total_flos": 1258233913036800.0,
|
| 14 |
+
"train_loss": 1.552238972981771,
|
| 15 |
+
"train_runtime": 328.4713,
|
| 16 |
+
"train_samples_per_second": 4.11,
|
| 17 |
+
"train_steps_per_second": 1.096
|
| 18 |
+
}
|
| 19 |
+
],
|
| 20 |
+
"max_steps": 360,
|
| 21 |
+
"num_train_epochs": 30,
|
| 22 |
+
"total_flos": 1258233913036800.0,
|
| 23 |
+
"trial_name": null,
|
| 24 |
+
"trial_params": null
|
| 25 |
+
}
|