Training in progress, epoch 0
Browse files- all_results.json +7 -0
- pytorch_model.bin +1 -1
- train_results.json +7 -0
- trainer_state.json +46 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.96,
|
| 3 |
+
"train_loss": 0.557555191218853,
|
| 4 |
+
"train_runtime": 365.4124,
|
| 5 |
+
"train_samples_per_second": 1.086,
|
| 6 |
+
"train_steps_per_second": 0.033
|
| 7 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 350919226
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0235bf869e7c7b9c4826e7d5347936f6562466fed732304cb3879de9629d44af
|
| 3 |
size 350919226
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.96,
|
| 3 |
+
"train_loss": 0.557555191218853,
|
| 4 |
+
"train_runtime": 365.4124,
|
| 5 |
+
"train_samples_per_second": 1.086,
|
| 6 |
+
"train_steps_per_second": 0.033
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "1-finetuned-spiderTraining5-100/checkpoint-12",
|
| 4 |
+
"epoch": 0.96,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 12,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8,
|
| 13 |
+
"learning_rate": 0.0001,
|
| 14 |
+
"loss": 0.6503,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.96,
|
| 19 |
+
"eval_accuracy": 1.0,
|
| 20 |
+
"eval_f1": 1.0,
|
| 21 |
+
"eval_loss": 0.03290669620037079,
|
| 22 |
+
"eval_precision": 1.0,
|
| 23 |
+
"eval_recall": 1.0,
|
| 24 |
+
"eval_runtime": 4.4674,
|
| 25 |
+
"eval_samples_per_second": 11.192,
|
| 26 |
+
"eval_steps_per_second": 1.567,
|
| 27 |
+
"step": 12
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.96,
|
| 31 |
+
"step": 12,
|
| 32 |
+
"total_flos": 8.93831171014656e+16,
|
| 33 |
+
"train_loss": 0.557555191218853,
|
| 34 |
+
"train_runtime": 365.4124,
|
| 35 |
+
"train_samples_per_second": 1.086,
|
| 36 |
+
"train_steps_per_second": 0.033
|
| 37 |
+
}
|
| 38 |
+
],
|
| 39 |
+
"logging_steps": 10,
|
| 40 |
+
"max_steps": 12,
|
| 41 |
+
"num_train_epochs": 1,
|
| 42 |
+
"save_steps": 500,
|
| 43 |
+
"total_flos": 8.93831171014656e+16,
|
| 44 |
+
"trial_name": null,
|
| 45 |
+
"trial_params": null
|
| 46 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4472
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fa8148344735d784211bc7d9b25cdd8e7698300a5919f32f19e461327d776ba
|
| 3 |
size 4472
|