Training in progress, epoch 3, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346293856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:994af4ef7e2e21f7bab319c9006c4111aceb192de8105891aa574e895d2c3eef
|
| 3 |
size 346293856
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 16,
|
| 3 |
"best_metric": 0.8204972743988037,
|
| 4 |
"best_model_checkpoint": "./finetuning/checkpoint-16",
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -47,6 +47,22 @@
|
|
| 47 |
"eval_samples_per_second": 20.206,
|
| 48 |
"eval_steps_per_second": 1.263,
|
| 49 |
"step": 32
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"logging_steps": 10,
|
|
@@ -61,7 +77,7 @@
|
|
| 61 |
"early_stopping_threshold": 0.0
|
| 62 |
},
|
| 63 |
"attributes": {
|
| 64 |
-
"early_stopping_patience_counter":
|
| 65 |
}
|
| 66 |
},
|
| 67 |
"TrainerControl": {
|
|
@@ -70,12 +86,12 @@
|
|
| 70 |
"should_evaluate": false,
|
| 71 |
"should_log": false,
|
| 72 |
"should_save": true,
|
| 73 |
-
"should_training_stop":
|
| 74 |
},
|
| 75 |
"attributes": {}
|
| 76 |
}
|
| 77 |
},
|
| 78 |
-
"total_flos": 1.
|
| 79 |
"train_batch_size": 512,
|
| 80 |
"trial_name": null,
|
| 81 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 16,
|
| 3 |
"best_metric": 0.8204972743988037,
|
| 4 |
"best_model_checkpoint": "./finetuning/checkpoint-16",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 48,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 47 |
"eval_samples_per_second": 20.206,
|
| 48 |
"eval_steps_per_second": 1.263,
|
| 49 |
"step": 32
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 2.5,
|
| 53 |
+
"grad_norm": 0.7750149965286255,
|
| 54 |
+
"learning_rate": 3.78125e-05,
|
| 55 |
+
"loss": 0.25730888843536376,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.785,
|
| 61 |
+
"eval_loss": 0.8522552847862244,
|
| 62 |
+
"eval_runtime": 98.5747,
|
| 63 |
+
"eval_samples_per_second": 20.289,
|
| 64 |
+
"eval_steps_per_second": 1.268,
|
| 65 |
+
"step": 48
|
| 66 |
}
|
| 67 |
],
|
| 68 |
"logging_steps": 10,
|
|
|
|
| 77 |
"early_stopping_threshold": 0.0
|
| 78 |
},
|
| 79 |
"attributes": {
|
| 80 |
+
"early_stopping_patience_counter": 2
|
| 81 |
}
|
| 82 |
},
|
| 83 |
"TrainerControl": {
|
|
|
|
| 86 |
"should_evaluate": false,
|
| 87 |
"should_log": false,
|
| 88 |
"should_save": true,
|
| 89 |
+
"should_training_stop": true
|
| 90 |
},
|
| 91 |
"attributes": {}
|
| 92 |
}
|
| 93 |
},
|
| 94 |
+
"total_flos": 1.876443281620992e+18,
|
| 95 |
"train_batch_size": 512,
|
| 96 |
"trial_name": null,
|
| 97 |
"trial_params": null
|