Training in progress, step 6360, 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 sha256:9652c3873aa510e2f665f8957dddc2627872caea99fbc5ee6613d9686112cb03
|
| 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 sha256:9094123d8a9176c76a002d58b523503209dd99665a1c687f689e84d0f9f59127
|
| 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 sha256:2d06f2a62596ce617ea20a286c6f39b65f10cfcc3a6a9dbd5159f3a031e3957f
|
| 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,
|
|
@@ -11438,6 +11438,24 @@
|
|
| 11438 |
"mean_token_accuracy": 0.6340841352939606,
|
| 11439 |
"num_tokens": 23156832.0,
|
| 11440 |
"step": 6350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11441 |
}
|
| 11442 |
],
|
| 11443 |
"logging_steps": 5,
|
|
@@ -11457,7 +11475,7 @@
|
|
| 11457 |
"attributes": {}
|
| 11458 |
}
|
| 11459 |
},
|
| 11460 |
-
"total_flos": 1.
|
| 11461 |
"train_batch_size": 4,
|
| 11462 |
"trial_name": null,
|
| 11463 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11438 |
"mean_token_accuracy": 0.6340841352939606,
|
| 11439 |
"num_tokens": 23156832.0,
|
| 11440 |
"step": 6350
|
| 11441 |
+
},
|
| 11442 |
+
{
|
| 11443 |
+
"epoch": 48.88461538461539,
|
| 11444 |
+
"grad_norm": 0.0,
|
| 11445 |
+
"learning_rate": 1.823e-05,
|
| 11446 |
+
"loss": 1.6869,
|
| 11447 |
+
"mean_token_accuracy": 0.6609957993030549,
|
| 11448 |
+
"num_tokens": 23175409.0,
|
| 11449 |
+
"step": 6355
|
| 11450 |
+
},
|
| 11451 |
+
{
|
| 11452 |
+
"epoch": 48.92307692307692,
|
| 11453 |
+
"grad_norm": 0.0,
|
| 11454 |
+
"learning_rate": 1.8205e-05,
|
| 11455 |
+
"loss": 1.7518,
|
| 11456 |
+
"mean_token_accuracy": 0.6469810694456101,
|
| 11457 |
+
"num_tokens": 23193876.0,
|
| 11458 |
+
"step": 6360
|
| 11459 |
}
|
| 11460 |
],
|
| 11461 |
"logging_steps": 5,
|
|
|
|
| 11475 |
"attributes": {}
|
| 11476 |
}
|
| 11477 |
},
|
| 11478 |
+
"total_flos": 1.1757346495812403e+18,
|
| 11479 |
"train_batch_size": 4,
|
| 11480 |
"trial_name": null,
|
| 11481 |
"trial_params": null
|