Training in progress, step 7310, 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 sha256:586bf1d370b83287544877ec1110f9d473e985c811bf1db44ad548cc446f7edd
|
| 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 sha256:5665977e2560b557a564be416133fe5621b4bb183fc9117f301e3e019d2a8e4e
|
| 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 sha256:67bf204f3f6c86809e2cdaf6dcf42ebd3201aa72d82cb37b7376eb434ee50b04
|
| 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": 56.
|
| 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,
|
|
@@ -13148,6 +13148,24 @@
|
|
| 13148 |
"mean_token_accuracy": 0.6660002678632736,
|
| 13149 |
"num_tokens": 26622949.0,
|
| 13150 |
"step": 7300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13151 |
}
|
| 13152 |
],
|
| 13153 |
"logging_steps": 5,
|
|
@@ -13167,7 +13185,7 @@
|
|
| 13167 |
"attributes": {}
|
| 13168 |
}
|
| 13169 |
},
|
| 13170 |
-
"total_flos": 1.
|
| 13171 |
"train_batch_size": 4,
|
| 13172 |
"trial_name": null,
|
| 13173 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13148 |
"mean_token_accuracy": 0.6660002678632736,
|
| 13149 |
"num_tokens": 26622949.0,
|
| 13150 |
"step": 7300
|
| 13151 |
+
},
|
| 13152 |
+
{
|
| 13153 |
+
"epoch": 56.19230769230769,
|
| 13154 |
+
"grad_norm": 0.0,
|
| 13155 |
+
"learning_rate": 1.3480000000000001e-05,
|
| 13156 |
+
"loss": 1.7609,
|
| 13157 |
+
"mean_token_accuracy": 0.6495236337184906,
|
| 13158 |
+
"num_tokens": 26640892.0,
|
| 13159 |
+
"step": 7305
|
| 13160 |
+
},
|
| 13161 |
+
{
|
| 13162 |
+
"epoch": 56.23076923076923,
|
| 13163 |
+
"grad_norm": 0.0,
|
| 13164 |
+
"learning_rate": 1.3455e-05,
|
| 13165 |
+
"loss": 1.7394,
|
| 13166 |
+
"mean_token_accuracy": 0.6511315196752548,
|
| 13167 |
+
"num_tokens": 26659096.0,
|
| 13168 |
+
"step": 7310
|
| 13169 |
}
|
| 13170 |
],
|
| 13171 |
"logging_steps": 5,
|
|
|
|
| 13185 |
"attributes": {}
|
| 13186 |
}
|
| 13187 |
},
|
| 13188 |
+
"total_flos": 1.351661784836014e+18,
|
| 13189 |
"train_batch_size": 4,
|
| 13190 |
"trial_name": null,
|
| 13191 |
"trial_params": null
|