Training in progress, step 6780, 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:d79cdd8e831c8022642ff50d42a44810f5414e6a710d38c59da6d2102be9bf71
|
| 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 sha256:5e1526a80f98fa77c1a8ddfa2f3c1af3e31acc043ea1eb92a7eb02862fe6d060
|
| 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 sha256:76db890c49e67211dba19dbdb5477c4f8424941d811b9b66d4a050661f4aaf54
|
| 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": 52.
|
| 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,
|
|
@@ -12194,6 +12194,24 @@
|
|
| 12194 |
"mean_token_accuracy": 0.6482141762971878,
|
| 12195 |
"num_tokens": 24690768.0,
|
| 12196 |
"step": 6770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12197 |
}
|
| 12198 |
],
|
| 12199 |
"logging_steps": 5,
|
|
@@ -12213,7 +12231,7 @@
|
|
| 12213 |
"attributes": {}
|
| 12214 |
}
|
| 12215 |
},
|
| 12216 |
-
"total_flos": 1.
|
| 12217 |
"train_batch_size": 4,
|
| 12218 |
"trial_name": null,
|
| 12219 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12194 |
"mean_token_accuracy": 0.6482141762971878,
|
| 12195 |
"num_tokens": 24690768.0,
|
| 12196 |
"step": 6770
|
| 12197 |
+
},
|
| 12198 |
+
{
|
| 12199 |
+
"epoch": 52.11538461538461,
|
| 12200 |
+
"grad_norm": 0.0,
|
| 12201 |
+
"learning_rate": 1.613e-05,
|
| 12202 |
+
"loss": 1.6709,
|
| 12203 |
+
"mean_token_accuracy": 0.6655151665210723,
|
| 12204 |
+
"num_tokens": 24709986.0,
|
| 12205 |
+
"step": 6775
|
| 12206 |
+
},
|
| 12207 |
+
{
|
| 12208 |
+
"epoch": 52.15384615384615,
|
| 12209 |
+
"grad_norm": 0.0,
|
| 12210 |
+
"learning_rate": 1.6105e-05,
|
| 12211 |
+
"loss": 1.8157,
|
| 12212 |
+
"mean_token_accuracy": 0.6377092868089675,
|
| 12213 |
+
"num_tokens": 24726980.0,
|
| 12214 |
+
"step": 6780
|
| 12215 |
}
|
| 12216 |
],
|
| 12217 |
"logging_steps": 5,
|
|
|
|
| 12231 |
"attributes": {}
|
| 12232 |
}
|
| 12233 |
},
|
| 12234 |
+
"total_flos": 1.2536958455016653e+18,
|
| 12235 |
"train_batch_size": 4,
|
| 12236 |
"trial_name": null,
|
| 12237 |
"trial_params": null
|