End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 4.265636444091797,
|
| 4 |
+
"eval_runtime": 7.3939,
|
| 5 |
+
"eval_samples_per_second": 147.959,
|
| 6 |
+
"eval_steps_per_second": 2.434,
|
| 7 |
+
"train_loss": 0.9768911893060318,
|
| 8 |
+
"train_runtime": 400.4654,
|
| 9 |
+
"train_samples_per_second": 65.429,
|
| 10 |
+
"train_steps_per_second": 1.026
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 4.265636444091797,
|
| 4 |
+
"eval_runtime": 7.3939,
|
| 5 |
+
"eval_samples_per_second": 147.959,
|
| 6 |
+
"eval_steps_per_second": 2.434
|
| 7 |
+
}
|
runs/Apr11_22-49-07_e01fb89ad7ea/events.out.tfevents.1649717858.e01fb89ad7ea.3113.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69a285e9bbf0ca6d22bf0dbc9b710488988f7e5c90829aced18509dabc13240
|
| 3 |
+
size 311
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.9768911893060318,
|
| 4 |
+
"train_runtime": 400.4654,
|
| 5 |
+
"train_samples_per_second": 65.429,
|
| 6 |
+
"train_steps_per_second": 1.026
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 411,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.73,
|
| 12 |
+
"learning_rate": 4.21409214092141e-05,
|
| 13 |
+
"loss": 1.6779,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.46,
|
| 18 |
+
"learning_rate": 2.859078590785908e-05,
|
| 19 |
+
"loss": 1.0913,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.19,
|
| 24 |
+
"learning_rate": 1.5040650406504067e-05,
|
| 25 |
+
"loss": 0.7497,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.92,
|
| 30 |
+
"learning_rate": 1.4905149051490515e-06,
|
| 31 |
+
"loss": 0.4489,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.0,
|
| 36 |
+
"step": 411,
|
| 37 |
+
"total_flos": 633388750422912.0,
|
| 38 |
+
"train_loss": 0.9768911893060318,
|
| 39 |
+
"train_runtime": 400.4654,
|
| 40 |
+
"train_samples_per_second": 65.429,
|
| 41 |
+
"train_steps_per_second": 1.026
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"max_steps": 411,
|
| 45 |
+
"num_train_epochs": 3,
|
| 46 |
+
"total_flos": 633388750422912.0,
|
| 47 |
+
"trial_name": null,
|
| 48 |
+
"trial_params": null
|
| 49 |
+
}
|