Training in progress, step 7950, 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:c050c18e9825b82f0638af95438df90cd7c31b5b383b3dd7a11c34733fa02fb1
|
| 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 sha256:65a897d1e0d95e54642241004208135b4d711d033251fb8278c1422451a81d0e
|
| 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 sha256:434b1f3ab4547da278f19dc2126d90add50095bdd1a54abda18ed560835f2779
|
| 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": 61.
|
| 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,
|
|
@@ -14300,6 +14300,24 @@
|
|
| 14300 |
"mean_token_accuracy": 0.6357664644718171,
|
| 14301 |
"num_tokens": 28955347.0,
|
| 14302 |
"step": 7940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14303 |
}
|
| 14304 |
],
|
| 14305 |
"logging_steps": 5,
|
|
@@ -14319,7 +14337,7 @@
|
|
| 14319 |
"attributes": {}
|
| 14320 |
}
|
| 14321 |
},
|
| 14322 |
-
"total_flos": 1.
|
| 14323 |
"train_batch_size": 4,
|
| 14324 |
"trial_name": null,
|
| 14325 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14300 |
"mean_token_accuracy": 0.6357664644718171,
|
| 14301 |
"num_tokens": 28955347.0,
|
| 14302 |
"step": 7940
|
| 14303 |
+
},
|
| 14304 |
+
{
|
| 14305 |
+
"epoch": 61.11538461538461,
|
| 14306 |
+
"grad_norm": 0.0,
|
| 14307 |
+
"learning_rate": 1.0280000000000002e-05,
|
| 14308 |
+
"loss": 1.7796,
|
| 14309 |
+
"mean_token_accuracy": 0.6469300240278244,
|
| 14310 |
+
"num_tokens": 28972764.0,
|
| 14311 |
+
"step": 7945
|
| 14312 |
+
},
|
| 14313 |
+
{
|
| 14314 |
+
"epoch": 61.15384615384615,
|
| 14315 |
+
"grad_norm": 0.0,
|
| 14316 |
+
"learning_rate": 1.0255000000000001e-05,
|
| 14317 |
+
"loss": 1.7454,
|
| 14318 |
+
"mean_token_accuracy": 0.6496328443288804,
|
| 14319 |
+
"num_tokens": 28991130.0,
|
| 14320 |
+
"step": 7950
|
| 14321 |
}
|
| 14322 |
],
|
| 14323 |
"logging_steps": 5,
|
|
|
|
| 14337 |
"attributes": {}
|
| 14338 |
}
|
| 14339 |
},
|
| 14340 |
+
"total_flos": 1.4699112837650842e+18,
|
| 14341 |
"train_batch_size": 4,
|
| 14342 |
"trial_name": null,
|
| 14343 |
"trial_params": null
|