Training in progress, step 2320, 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 sha256:2253ef03cfb4445108c28024ff48558b995b2be5252ebdb729450e7133c66e87
|
| 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 sha256:16770fb435a62cd3ce08f018d483b662dbefbedb96182c133c450c698a1dcca4
|
| 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 sha256:54190cefc309f7695135f65604c7b157c1352bbbf8cdc51be7c8935b16eb6af6
|
| 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,
|
|
@@ -4166,6 +4166,24 @@
|
|
| 4166 |
"mean_token_accuracy": 0.641442459821701,
|
| 4167 |
"num_tokens": 8425390.0,
|
| 4168 |
"step": 2310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4169 |
}
|
| 4170 |
],
|
| 4171 |
"logging_steps": 5,
|
|
@@ -4185,7 +4203,7 @@
|
|
| 4185 |
"attributes": {}
|
| 4186 |
}
|
| 4187 |
},
|
| 4188 |
-
"total_flos": 4.
|
| 4189 |
"train_batch_size": 4,
|
| 4190 |
"trial_name": null,
|
| 4191 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4166 |
"mean_token_accuracy": 0.641442459821701,
|
| 4167 |
"num_tokens": 8425390.0,
|
| 4168 |
"step": 2310
|
| 4169 |
+
},
|
| 4170 |
+
{
|
| 4171 |
+
"epoch": 17.807692307692307,
|
| 4172 |
+
"grad_norm": 0.0,
|
| 4173 |
+
"learning_rate": 3.8429999999999996e-05,
|
| 4174 |
+
"loss": 1.7467,
|
| 4175 |
+
"mean_token_accuracy": 0.6489367455244064,
|
| 4176 |
+
"num_tokens": 8443863.0,
|
| 4177 |
+
"step": 2315
|
| 4178 |
+
},
|
| 4179 |
+
{
|
| 4180 |
+
"epoch": 17.846153846153847,
|
| 4181 |
+
"grad_norm": 0.0,
|
| 4182 |
+
"learning_rate": 3.8405e-05,
|
| 4183 |
+
"loss": 1.8034,
|
| 4184 |
+
"mean_token_accuracy": 0.6354307472705841,
|
| 4185 |
+
"num_tokens": 8461483.0,
|
| 4186 |
+
"step": 2320
|
| 4187 |
}
|
| 4188 |
],
|
| 4189 |
"logging_steps": 5,
|
|
|
|
| 4203 |
"attributes": {}
|
| 4204 |
}
|
| 4205 |
},
|
| 4206 |
+
"total_flos": 4.287954691945267e+17,
|
| 4207 |
"train_batch_size": 4,
|
| 4208 |
"trial_name": null,
|
| 4209 |
"trial_params": null
|