Kerem P
commited on
Commit
•
b7a00ae
1
Parent(s):
cdd5601
Training in progress, epoch 1
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +40 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 3.448119721589265,
|
| 4 |
+
"train_runtime": 810.4417,
|
| 5 |
+
"train_samples": 1725,
|
| 6 |
+
"train_samples_per_second": 10.642,
|
| 7 |
+
"train_steps_per_second": 0.666
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3537954741
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b23628a194cde8be6276ce646120068823425254f1338d996d3b2c9e28457e80
|
| 3 |
size 3537954741
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 3.448119721589265,
|
| 4 |
+
"train_runtime": 810.4417,
|
| 5 |
+
"train_samples": 1725,
|
| 6 |
+
"train_samples_per_second": 10.642,
|
| 7 |
+
"train_steps_per_second": 0.666
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 540,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.85,
|
| 13 |
+
"learning_rate": 3.148148148148148e-05,
|
| 14 |
+
"loss": 3.4743,
|
| 15 |
+
"step": 200
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 3.7,
|
| 19 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 20 |
+
"loss": 3.4332,
|
| 21 |
+
"step": 400
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 5.0,
|
| 25 |
+
"step": 540,
|
| 26 |
+
"total_flos": 0.0,
|
| 27 |
+
"train_loss": 3.448119721589265,
|
| 28 |
+
"train_runtime": 810.4417,
|
| 29 |
+
"train_samples_per_second": 10.642,
|
| 30 |
+
"train_steps_per_second": 0.666
|
| 31 |
+
}
|
| 32 |
+
],
|
| 33 |
+
"logging_steps": 200,
|
| 34 |
+
"max_steps": 540,
|
| 35 |
+
"num_train_epochs": 5,
|
| 36 |
+
"save_steps": 500,
|
| 37 |
+
"total_flos": 0.0,
|
| 38 |
+
"trial_name": null,
|
| 39 |
+
"trial_params": null
|
| 40 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a122695a1a1fd5f034c84a26bcfe5e01f34efefc817debb31a2d70fda652ab27
|
| 3 |
size 4091
|