Training completed
Browse files- README.md +3 -3
- all_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +9 -9
README.md
CHANGED
|
@@ -37,11 +37,11 @@ More information needed
|
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 5e-05
|
| 40 |
-
- train_batch_size:
|
| 41 |
-
- eval_batch_size:
|
| 42 |
- seed: 42
|
| 43 |
- gradient_accumulation_steps: 10
|
| 44 |
-
- total_train_batch_size:
|
| 45 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_ratio: 0.03
|
|
|
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
- gradient_accumulation_steps: 10
|
| 44 |
+
- total_train_batch_size: 20
|
| 45 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_ratio: 0.03
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0.
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.00228310502283105,
|
| 3 |
+
"total_flos": 6957230456832000.0,
|
| 4 |
+
"train_loss": 10.657806396484375,
|
| 5 |
+
"train_runtime": 130.9955,
|
| 6 |
+
"train_samples_per_second": 1.527,
|
| 7 |
+
"train_steps_per_second": 0.076
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0.
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 0.00228310502283105,
|
| 3 |
+
"total_flos": 6957230456832000.0,
|
| 4 |
+
"train_loss": 10.657806396484375,
|
| 5 |
+
"train_runtime": 130.9955,
|
| 6 |
+
"train_samples_per_second": 1.527,
|
| 7 |
+
"train_steps_per_second": 0.076
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 0,
|
| 7 |
"global_step": 10,
|
| 8 |
"is_hyper_param_search": false,
|
|
@@ -10,13 +10,13 @@
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
"step": 10,
|
| 15 |
-
"total_flos":
|
| 16 |
-
"train_loss":
|
| 17 |
-
"train_runtime":
|
| 18 |
-
"train_samples_per_second":
|
| 19 |
-
"train_steps_per_second": 0.
|
| 20 |
}
|
| 21 |
],
|
| 22 |
"logging_steps": 100,
|
|
@@ -36,8 +36,8 @@
|
|
| 36 |
"attributes": {}
|
| 37 |
}
|
| 38 |
},
|
| 39 |
-
"total_flos":
|
| 40 |
-
"train_batch_size":
|
| 41 |
"trial_name": null,
|
| 42 |
"trial_params": null
|
| 43 |
}
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.00228310502283105,
|
| 6 |
"eval_steps": 0,
|
| 7 |
"global_step": 10,
|
| 8 |
"is_hyper_param_search": false,
|
|
|
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.00228310502283105,
|
| 14 |
"step": 10,
|
| 15 |
+
"total_flos": 6957230456832000.0,
|
| 16 |
+
"train_loss": 10.657806396484375,
|
| 17 |
+
"train_runtime": 130.9955,
|
| 18 |
+
"train_samples_per_second": 1.527,
|
| 19 |
+
"train_steps_per_second": 0.076
|
| 20 |
}
|
| 21 |
],
|
| 22 |
"logging_steps": 100,
|
|
|
|
| 36 |
"attributes": {}
|
| 37 |
}
|
| 38 |
},
|
| 39 |
+
"total_flos": 6957230456832000.0,
|
| 40 |
+
"train_batch_size": 2,
|
| 41 |
"trial_name": null,
|
| 42 |
"trial_params": null
|
| 43 |
}
|