Commit
•
90a3c5c
1
Parent(s):
85a2002
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 0.9623739123344421,
|
| 5 |
+
"eval_runtime": 0.2051,
|
| 6 |
+
"eval_samples": 2,
|
| 7 |
+
"eval_samples_per_second": 9.752,
|
| 8 |
+
"eval_steps_per_second": 4.876,
|
| 9 |
+
"perplexity": 2.61790377677711,
|
| 10 |
+
"train_loss": 1.5763432820638021,
|
| 11 |
+
"train_runtime": 801.7351,
|
| 12 |
+
"train_samples": 111,
|
| 13 |
+
"train_samples_per_second": 4.153,
|
| 14 |
+
"train_steps_per_second": 1.048
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 0.9623739123344421,
|
| 5 |
+
"eval_runtime": 0.2051,
|
| 6 |
+
"eval_samples": 2,
|
| 7 |
+
"eval_samples_per_second": 9.752,
|
| 8 |
+
"eval_steps_per_second": 4.876,
|
| 9 |
+
"perplexity": 2.61790377677711
|
| 10 |
+
}
|
runs/Apr23_11-03-18_aa757fee724d/events.out.tfevents.1682248816.aa757fee724d.67087.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51c7acb2c4bf8e47d99cf94703a45cb0fac462dd46516e7cf8e16ed31a84a623
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"train_loss": 1.5763432820638021,
|
| 4 |
+
"train_runtime": 801.7351,
|
| 5 |
+
"train_samples": 111,
|
| 6 |
+
"train_samples_per_second": 4.153,
|
| 7 |
+
"train_steps_per_second": 1.048
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"global_step": 840,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 17.86,
|
| 12 |
+
"learning_rate": 2.023809523809524e-05,
|
| 13 |
+
"loss": 1.8057,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 30.0,
|
| 18 |
+
"step": 840,
|
| 19 |
+
"total_flos": 3103643652157440.0,
|
| 20 |
+
"train_loss": 1.5763432820638021,
|
| 21 |
+
"train_runtime": 801.7351,
|
| 22 |
+
"train_samples_per_second": 4.153,
|
| 23 |
+
"train_steps_per_second": 1.048
|
| 24 |
+
}
|
| 25 |
+
],
|
| 26 |
+
"max_steps": 840,
|
| 27 |
+
"num_train_epochs": 30,
|
| 28 |
+
"total_flos": 3103643652157440.0,
|
| 29 |
+
"trial_name": null,
|
| 30 |
+
"trial_params": null
|
| 31 |
+
}
|