Training in progress, epoch 2, 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 sha256:1eabafa569b98c15b9f47fac0510ad11474e5bf2f63a5216e137fe6ed6e3a053
|
| 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,
|
|
@@ -24,6 +24,29 @@
|
|
| 24 |
"eval_samples_per_second": 19.738,
|
| 25 |
"eval_steps_per_second": 1.234,
|
| 26 |
"step": 16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
| 28 |
],
|
| 29 |
"logging_steps": 10,
|
|
@@ -38,7 +61,7 @@
|
|
| 38 |
"early_stopping_threshold": 0.0
|
| 39 |
},
|
| 40 |
"attributes": {
|
| 41 |
-
"early_stopping_patience_counter":
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"TrainerControl": {
|
|
@@ -52,7 +75,7 @@
|
|
| 52 |
"attributes": {}
|
| 53 |
}
|
| 54 |
},
|
| 55 |
-
"total_flos":
|
| 56 |
"train_batch_size": 512,
|
| 57 |
"trial_name": null,
|
| 58 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 16,
|
| 3 |
"best_metric": 0.8204972743988037,
|
| 4 |
"best_model_checkpoint": "./finetuning/checkpoint-16",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 32,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 24 |
"eval_samples_per_second": 19.738,
|
| 25 |
"eval_steps_per_second": 1.234,
|
| 26 |
"step": 16
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.25,
|
| 30 |
+
"grad_norm": 1.2275031805038452,
|
| 31 |
+
"learning_rate": 4.40625e-05,
|
| 32 |
+
"loss": 0.5976850986480713,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.875,
|
| 37 |
+
"grad_norm": 1.2741576433181763,
|
| 38 |
+
"learning_rate": 4.09375e-05,
|
| 39 |
+
"loss": 0.36108148097991943,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.0,
|
| 44 |
+
"eval_accuracy": 0.784,
|
| 45 |
+
"eval_loss": 0.837196409702301,
|
| 46 |
+
"eval_runtime": 98.979,
|
| 47 |
+
"eval_samples_per_second": 20.206,
|
| 48 |
+
"eval_steps_per_second": 1.263,
|
| 49 |
+
"step": 32
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"logging_steps": 10,
|
|
|
|
| 61 |
"early_stopping_threshold": 0.0
|
| 62 |
},
|
| 63 |
"attributes": {
|
| 64 |
+
"early_stopping_patience_counter": 1
|
| 65 |
}
|
| 66 |
},
|
| 67 |
"TrainerControl": {
|
|
|
|
| 75 |
"attributes": {}
|
| 76 |
}
|
| 77 |
},
|
| 78 |
+
"total_flos": 1.250962187747328e+18,
|
| 79 |
"train_batch_size": 512,
|
| 80 |
"trial_name": null,
|
| 81 |
"trial_params": null
|