End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9976642888706521,
|
| 4 |
+
"eval_loss": 0.012173255905508995,
|
| 5 |
+
"eval_runtime": 6.4841,
|
| 6 |
+
"eval_samples": 1116,
|
| 7 |
+
"eval_samples_per_second": 172.113,
|
| 8 |
+
"eval_steps_per_second": 21.591,
|
| 9 |
+
"perplexity": 1.012247651557798,
|
| 10 |
+
"train_loss": 0.5359815748328837,
|
| 11 |
+
"train_runtime": 261.4152,
|
| 12 |
+
"train_samples": 6259,
|
| 13 |
+
"train_samples_per_second": 71.828,
|
| 14 |
+
"train_steps_per_second": 2.238
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9976642888706521,
|
| 4 |
+
"eval_loss": 0.012173255905508995,
|
| 5 |
+
"eval_runtime": 6.4841,
|
| 6 |
+
"eval_samples": 1116,
|
| 7 |
+
"eval_samples_per_second": 172.113,
|
| 8 |
+
"eval_steps_per_second": 21.591,
|
| 9 |
+
"perplexity": 1.012247651557798
|
| 10 |
+
}
|
runs/Apr24_11-02-30_2c630289b464/events.out.tfevents.1650798519.2c630289b464.12394.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82059578e0271edaa9afc5d1cd813a1cf9e434f005915e043c4afdb441c31f8d
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.5359815748328837,
|
| 4 |
+
"train_runtime": 261.4152,
|
| 5 |
+
"train_samples": 6259,
|
| 6 |
+
"train_samples_per_second": 71.828,
|
| 7 |
+
"train_steps_per_second": 2.238
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.012173255905508995,
|
| 3 |
+
"best_model_checkpoint": "models/checkpoint-585",
|
| 4 |
+
"epoch": 2.996168582375479,
|
| 5 |
+
"global_step": 585,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.9789031977498615,
|
| 13 |
+
"eval_loss": 0.11250920593738556,
|
| 14 |
+
"eval_runtime": 6.4785,
|
| 15 |
+
"eval_samples_per_second": 172.263,
|
| 16 |
+
"eval_steps_per_second": 21.61,
|
| 17 |
+
"step": 195
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_accuracy": 0.9973135814938732,
|
| 22 |
+
"eval_loss": 0.014149832539260387,
|
| 23 |
+
"eval_runtime": 6.3842,
|
| 24 |
+
"eval_samples_per_second": 174.807,
|
| 25 |
+
"eval_steps_per_second": 21.929,
|
| 26 |
+
"step": 390
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.56,
|
| 30 |
+
"learning_rate": 7.264957264957266e-06,
|
| 31 |
+
"loss": 0.6233,
|
| 32 |
+
"step": 500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.0,
|
| 36 |
+
"eval_accuracy": 0.9976642888706521,
|
| 37 |
+
"eval_loss": 0.012173255905508995,
|
| 38 |
+
"eval_runtime": 6.4332,
|
| 39 |
+
"eval_samples_per_second": 173.476,
|
| 40 |
+
"eval_steps_per_second": 21.762,
|
| 41 |
+
"step": 585
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"step": 585,
|
| 46 |
+
"total_flos": 1124510524133376.0,
|
| 47 |
+
"train_loss": 0.5359815748328837,
|
| 48 |
+
"train_runtime": 261.4152,
|
| 49 |
+
"train_samples_per_second": 71.828,
|
| 50 |
+
"train_steps_per_second": 2.238
|
| 51 |
+
}
|
| 52 |
+
],
|
| 53 |
+
"max_steps": 585,
|
| 54 |
+
"num_train_epochs": 3,
|
| 55 |
+
"total_flos": 1124510524133376.0,
|
| 56 |
+
"trial_name": null,
|
| 57 |
+
"trial_params": null
|
| 58 |
+
}
|