Training in progress, step 8030, 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:d5e262bd772a06c9edb796aeb817982961e64d5a83e2749330b2cf8894686da4
|
| 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 sha256:30ad11cfec3b31c55abbb5858b1840a11428f3c91861d8b239d7aab73a02c172
|
| 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:f74b849c12f57c73c45a4fc9ca83b483b0d6ea2ea322ecdd601cfda062917af4
|
| 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,
|
|
@@ -14444,6 +14444,24 @@
|
|
| 14444 |
"mean_token_accuracy": 0.6333356082439423,
|
| 14445 |
"num_tokens": 29247611.0,
|
| 14446 |
"step": 8020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14447 |
}
|
| 14448 |
],
|
| 14449 |
"logging_steps": 5,
|
|
@@ -14463,7 +14481,7 @@
|
|
| 14463 |
"attributes": {}
|
| 14464 |
}
|
| 14465 |
},
|
| 14466 |
-
"total_flos": 1.
|
| 14467 |
"train_batch_size": 4,
|
| 14468 |
"trial_name": null,
|
| 14469 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14444 |
"mean_token_accuracy": 0.6333356082439423,
|
| 14445 |
"num_tokens": 29247611.0,
|
| 14446 |
"step": 8020
|
| 14447 |
+
},
|
| 14448 |
+
{
|
| 14449 |
+
"epoch": 61.73076923076923,
|
| 14450 |
+
"grad_norm": 0.0,
|
| 14451 |
+
"learning_rate": 9.88e-06,
|
| 14452 |
+
"loss": 1.7164,
|
| 14453 |
+
"mean_token_accuracy": 0.6516272902488709,
|
| 14454 |
+
"num_tokens": 29265885.0,
|
| 14455 |
+
"step": 8025
|
| 14456 |
+
},
|
| 14457 |
+
{
|
| 14458 |
+
"epoch": 61.76923076923077,
|
| 14459 |
+
"grad_norm": 0.0,
|
| 14460 |
+
"learning_rate": 9.855e-06,
|
| 14461 |
+
"loss": 1.7593,
|
| 14462 |
+
"mean_token_accuracy": 0.6486380189657212,
|
| 14463 |
+
"num_tokens": 29284235.0,
|
| 14464 |
+
"step": 8030
|
| 14465 |
}
|
| 14466 |
],
|
| 14467 |
"logging_steps": 5,
|
|
|
|
| 14481 |
"attributes": {}
|
| 14482 |
}
|
| 14483 |
},
|
| 14484 |
+
"total_flos": 1.484731252937687e+18,
|
| 14485 |
"train_batch_size": 4,
|
| 14486 |
"trial_name": null,
|
| 14487 |
"trial_params": null
|