Training in progress, step 6320, 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:cebc3f61192810c45a3e7dabc2d31617ea95b6411355e7ba1c6c2065d2ee565a
|
| 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:b819728c674d3bc10d0030239858a078dd233b3650fe7f6c2e3de6fece1f144f
|
| 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 sha256:03451e72612bf9115d4820560ee2dc080fe5ec601d5ad1672e6905f8d22ac999
|
| 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": 48.
|
| 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,
|
|
@@ -11366,6 +11366,24 @@
|
|
| 11366 |
"mean_token_accuracy": 0.643173098564148,
|
| 11367 |
"num_tokens": 23012560.0,
|
| 11368 |
"step": 6310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11369 |
}
|
| 11370 |
],
|
| 11371 |
"logging_steps": 5,
|
|
@@ -11385,7 +11403,7 @@
|
|
| 11385 |
"attributes": {}
|
| 11386 |
}
|
| 11387 |
},
|
| 11388 |
-
"total_flos": 1.
|
| 11389 |
"train_batch_size": 4,
|
| 11390 |
"trial_name": null,
|
| 11391 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11366 |
"mean_token_accuracy": 0.643173098564148,
|
| 11367 |
"num_tokens": 23012560.0,
|
| 11368 |
"step": 6310
|
| 11369 |
+
},
|
| 11370 |
+
{
|
| 11371 |
+
"epoch": 48.57692307692308,
|
| 11372 |
+
"grad_norm": 0.0,
|
| 11373 |
+
"learning_rate": 1.843e-05,
|
| 11374 |
+
"loss": 1.7734,
|
| 11375 |
+
"mean_token_accuracy": 0.6458878636360168,
|
| 11376 |
+
"num_tokens": 23030129.0,
|
| 11377 |
+
"step": 6315
|
| 11378 |
+
},
|
| 11379 |
+
{
|
| 11380 |
+
"epoch": 48.61538461538461,
|
| 11381 |
+
"grad_norm": 0.0,
|
| 11382 |
+
"learning_rate": 1.8405e-05,
|
| 11383 |
+
"loss": 1.7598,
|
| 11384 |
+
"mean_token_accuracy": 0.6463797986507416,
|
| 11385 |
+
"num_tokens": 23047988.0,
|
| 11386 |
+
"step": 6320
|
| 11387 |
}
|
| 11388 |
],
|
| 11389 |
"logging_steps": 5,
|
|
|
|
| 11403 |
"attributes": {}
|
| 11404 |
}
|
| 11405 |
},
|
| 11406 |
+
"total_flos": 1.168271077033083e+18,
|
| 11407 |
"train_batch_size": 4,
|
| 11408 |
"trial_name": null,
|
| 11409 |
"trial_params": null
|