Commit
•
bdd2df5
1
Parent(s):
9e813ba
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.06506024096385542,
|
| 4 |
+
"eval_loss": 5.995445728302002,
|
| 5 |
+
"eval_runtime": 1.2236,
|
| 6 |
+
"eval_samples": 6,
|
| 7 |
+
"eval_samples_per_second": 4.904,
|
| 8 |
+
"eval_steps_per_second": 1.635,
|
| 9 |
+
"perplexity": 401.59564664926756,
|
| 10 |
+
"train_loss": 6.3856693662446125,
|
| 11 |
+
"train_runtime": 2805.3129,
|
| 12 |
+
"train_samples": 229,
|
| 13 |
+
"train_samples_per_second": 2.449,
|
| 14 |
+
"train_steps_per_second": 0.62
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.06506024096385542,
|
| 4 |
+
"eval_loss": 5.995445728302002,
|
| 5 |
+
"eval_runtime": 1.2236,
|
| 6 |
+
"eval_samples": 6,
|
| 7 |
+
"eval_samples_per_second": 4.904,
|
| 8 |
+
"eval_steps_per_second": 1.635,
|
| 9 |
+
"perplexity": 401.59564664926756
|
| 10 |
+
}
|
runs/Apr22_11-25-08_38be08d825d1/events.out.tfevents.1682165719.38be08d825d1.1385.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ff7bb0555fd94787a24e4fa81592a7475d208ad14e5b67e27ecee64e73e7843
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"train_loss": 6.3856693662446125,
|
| 4 |
+
"train_runtime": 2805.3129,
|
| 5 |
+
"train_samples": 229,
|
| 6 |
+
"train_samples_per_second": 2.449,
|
| 7 |
+
"train_steps_per_second": 0.62
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"global_step": 1740,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 8.62,
|
| 12 |
+
"learning_rate": 0.0003563218390804598,
|
| 13 |
+
"loss": 6.498,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 17.24,
|
| 18 |
+
"learning_rate": 0.00021264367816091953,
|
| 19 |
+
"loss": 6.3597,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 25.86,
|
| 24 |
+
"learning_rate": 6.896551724137931e-05,
|
| 25 |
+
"loss": 6.3417,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 30.0,
|
| 30 |
+
"step": 1740,
|
| 31 |
+
"total_flos": 6403012579676160.0,
|
| 32 |
+
"train_loss": 6.3856693662446125,
|
| 33 |
+
"train_runtime": 2805.3129,
|
| 34 |
+
"train_samples_per_second": 2.449,
|
| 35 |
+
"train_steps_per_second": 0.62
|
| 36 |
+
}
|
| 37 |
+
],
|
| 38 |
+
"max_steps": 1740,
|
| 39 |
+
"num_train_epochs": 30,
|
| 40 |
+
"total_flos": 6403012579676160.0,
|
| 41 |
+
"trial_name": null,
|
| 42 |
+
"trial_params": null
|
| 43 |
+
}
|