End of training
Browse files- all_results.json +17 -0
- eval_results.json +12 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +56 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9920953233908337,
|
| 4 |
+
"eval_f1": 0.952317215994646,
|
| 5 |
+
"eval_loss": 0.039794921875,
|
| 6 |
+
"eval_precision": 0.9467731204258151,
|
| 7 |
+
"eval_recall": 0.9579266240323123,
|
| 8 |
+
"eval_runtime": 8.5576,
|
| 9 |
+
"eval_samples": 3250,
|
| 10 |
+
"eval_samples_per_second": 379.781,
|
| 11 |
+
"eval_steps_per_second": 37.978,
|
| 12 |
+
"train_loss": 0.07335638256863196,
|
| 13 |
+
"train_runtime": 838.7854,
|
| 14 |
+
"train_samples": 14041,
|
| 15 |
+
"train_samples_per_second": 50.187,
|
| 16 |
+
"train_steps_per_second": 3.137
|
| 17 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.9920953233908337,
|
| 4 |
+
"eval_f1": 0.952317215994646,
|
| 5 |
+
"eval_loss": 0.039794921875,
|
| 6 |
+
"eval_precision": 0.9467731204258151,
|
| 7 |
+
"eval_recall": 0.9579266240323123,
|
| 8 |
+
"eval_runtime": 8.5576,
|
| 9 |
+
"eval_samples": 3250,
|
| 10 |
+
"eval_samples_per_second": 379.781,
|
| 11 |
+
"eval_steps_per_second": 37.978
|
| 12 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 248192241
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:571c37e02f1038e53a9d36e0e2f22dbad43f24f2cacf9aed48499066230f2fe2
|
| 3 |
size 248192241
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.07335638256863196,
|
| 4 |
+
"train_runtime": 838.7854,
|
| 5 |
+
"train_samples": 14041,
|
| 6 |
+
"train_samples_per_second": 50.187,
|
| 7 |
+
"train_steps_per_second": 3.137
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 2631,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.57,
|
| 12 |
+
"learning_rate": 4.0497909540098824e-05,
|
| 13 |
+
"loss": 0.2038,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.14,
|
| 18 |
+
"learning_rate": 3.0995819080197646e-05,
|
| 19 |
+
"loss": 0.0882,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.71,
|
| 24 |
+
"learning_rate": 2.1493728620296465e-05,
|
| 25 |
+
"loss": 0.0401,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.28,
|
| 30 |
+
"learning_rate": 1.1991638160395288e-05,
|
| 31 |
+
"loss": 0.0309,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.85,
|
| 36 |
+
"learning_rate": 2.489547700494109e-06,
|
| 37 |
+
"loss": 0.0173,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"step": 2631,
|
| 43 |
+
"total_flos": 1.7600391032419123e+17,
|
| 44 |
+
"train_loss": 0.07335638256863196,
|
| 45 |
+
"train_runtime": 838.7854,
|
| 46 |
+
"train_samples_per_second": 50.187,
|
| 47 |
+
"train_steps_per_second": 3.137
|
| 48 |
+
}
|
| 49 |
+
],
|
| 50 |
+
"max_steps": 2631,
|
| 51 |
+
"num_train_epochs": 3,
|
| 52 |
+
"start_time": 1660825259.040938,
|
| 53 |
+
"total_flos": 1.7600391032419123e+17,
|
| 54 |
+
"trial_name": null,
|
| 55 |
+
"trial_params": null
|
| 56 |
+
}
|