Training in progress, step 2330, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ba3dbeb521958f247e981cc9357a52110e692ab35b2ff47ce61fc13a022a8ed
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6084ebd3cb3522527fa2c390f77b4851a0e9bb98d51c9ad4df67f6cb6b062b2f
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:951f68ac0f8d14680c5fad40e4807c509c5a199dd5c51ce40e692df67b5c28da
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 17.
|
| 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,
|
|
@@ -4184,6 +4184,24 @@
|
|
| 4184 |
"mean_token_accuracy": 0.6354307472705841,
|
| 4185 |
"num_tokens": 8461483.0,
|
| 4186 |
"step": 2320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4187 |
}
|
| 4188 |
],
|
| 4189 |
"logging_steps": 5,
|
|
@@ -4203,7 +4221,7 @@
|
|
| 4203 |
"attributes": {}
|
| 4204 |
}
|
| 4205 |
},
|
| 4206 |
-
"total_flos": 4.
|
| 4207 |
"train_batch_size": 4,
|
| 4208 |
"trial_name": null,
|
| 4209 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4184 |
"mean_token_accuracy": 0.6354307472705841,
|
| 4185 |
"num_tokens": 8461483.0,
|
| 4186 |
"step": 2320
|
| 4187 |
+
},
|
| 4188 |
+
{
|
| 4189 |
+
"epoch": 17.884615384615383,
|
| 4190 |
+
"grad_norm": 0.0,
|
| 4191 |
+
"learning_rate": 3.838e-05,
|
| 4192 |
+
"loss": 1.7575,
|
| 4193 |
+
"mean_token_accuracy": 0.6472324639558792,
|
| 4194 |
+
"num_tokens": 8479006.0,
|
| 4195 |
+
"step": 2325
|
| 4196 |
+
},
|
| 4197 |
+
{
|
| 4198 |
+
"epoch": 17.923076923076923,
|
| 4199 |
+
"grad_norm": 0.0,
|
| 4200 |
+
"learning_rate": 3.8355e-05,
|
| 4201 |
+
"loss": 1.7741,
|
| 4202 |
+
"mean_token_accuracy": 0.646085774898529,
|
| 4203 |
+
"num_tokens": 8496986.0,
|
| 4204 |
+
"step": 2330
|
| 4205 |
}
|
| 4206 |
],
|
| 4207 |
"logging_steps": 5,
|
|
|
|
| 4221 |
"attributes": {}
|
| 4222 |
}
|
| 4223 |
},
|
| 4224 |
+
"total_flos": 4.3057316051582976e+17,
|
| 4225 |
"train_batch_size": 4,
|
| 4226 |
"trial_name": null,
|
| 4227 |
"trial_params": null
|