Training in progress, step 6310, 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 sha256:84f31297fbc3fb15fe73408e21e707c43d15354e9118f8d0ba42dae1d821e34d
|
| 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:ee7792d294db7ccba0dfcfaff0cc9cb033738b6f48f10d2f5244bb8966d31a3e
|
| 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 sha256:9522e30a614347925d9e8adb57e21e2c880bfb05eb6b66b4eb8c331e469b89c8
|
| 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,
|
|
@@ -11348,6 +11348,24 @@
|
|
| 11348 |
"mean_token_accuracy": 0.6526569038629532,
|
| 11349 |
"num_tokens": 22975073.0,
|
| 11350 |
"step": 6300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11351 |
}
|
| 11352 |
],
|
| 11353 |
"logging_steps": 5,
|
|
@@ -11367,7 +11385,7 @@
|
|
| 11367 |
"attributes": {}
|
| 11368 |
}
|
| 11369 |
},
|
| 11370 |
-
"total_flos": 1.
|
| 11371 |
"train_batch_size": 4,
|
| 11372 |
"trial_name": null,
|
| 11373 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11348 |
"mean_token_accuracy": 0.6526569038629532,
|
| 11349 |
"num_tokens": 22975073.0,
|
| 11350 |
"step": 6300
|
| 11351 |
+
},
|
| 11352 |
+
{
|
| 11353 |
+
"epoch": 48.5,
|
| 11354 |
+
"grad_norm": 0.0,
|
| 11355 |
+
"learning_rate": 1.848e-05,
|
| 11356 |
+
"loss": 1.7108,
|
| 11357 |
+
"mean_token_accuracy": 0.6544829219579696,
|
| 11358 |
+
"num_tokens": 22993939.0,
|
| 11359 |
+
"step": 6305
|
| 11360 |
+
},
|
| 11361 |
+
{
|
| 11362 |
+
"epoch": 48.53846153846154,
|
| 11363 |
+
"grad_norm": 0.0,
|
| 11364 |
+
"learning_rate": 1.8455e-05,
|
| 11365 |
+
"loss": 1.7625,
|
| 11366 |
+
"mean_token_accuracy": 0.643173098564148,
|
| 11367 |
+
"num_tokens": 23012560.0,
|
| 11368 |
+
"step": 6310
|
| 11369 |
}
|
| 11370 |
],
|
| 11371 |
"logging_steps": 5,
|
|
|
|
| 11385 |
"attributes": {}
|
| 11386 |
}
|
| 11387 |
},
|
| 11388 |
+
"total_flos": 1.166500689552507e+18,
|
| 11389 |
"train_batch_size": 4,
|
| 11390 |
"trial_name": null,
|
| 11391 |
"trial_params": null
|