Training in progress, step 9710, 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 sha256:80a932c2dc84d7e33a1f5cd7c04ce3af4e5eb0055f6e5e12964ab89013397a54
|
| 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:e46a9a3b1d82da16a4ab5aacca2653303eeab42e42ea9c88d2d876ddb7e8c0a6
|
| 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 sha256:51d25238b6f854d39bf5263f8c82bda41d604d34a5cb7f6c7477e59b04240403
|
| 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": 74.
|
| 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,
|
|
@@ -17468,6 +17468,24 @@
|
|
| 17468 |
"mean_token_accuracy": 0.6643463402986527,
|
| 17469 |
"num_tokens": 35375365.0,
|
| 17470 |
"step": 9700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17471 |
}
|
| 17472 |
],
|
| 17473 |
"logging_steps": 5,
|
|
@@ -17487,7 +17505,7 @@
|
|
| 17487 |
"attributes": {}
|
| 17488 |
}
|
| 17489 |
},
|
| 17490 |
-
"total_flos": 1.
|
| 17491 |
"train_batch_size": 4,
|
| 17492 |
"trial_name": null,
|
| 17493 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.6923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17468 |
"mean_token_accuracy": 0.6643463402986527,
|
| 17469 |
"num_tokens": 35375365.0,
|
| 17470 |
"step": 9700
|
| 17471 |
+
},
|
| 17472 |
+
{
|
| 17473 |
+
"epoch": 74.65384615384616,
|
| 17474 |
+
"grad_norm": 0.0,
|
| 17475 |
+
"learning_rate": 1.4800000000000002e-06,
|
| 17476 |
+
"loss": 1.7907,
|
| 17477 |
+
"mean_token_accuracy": 0.6419687926769256,
|
| 17478 |
+
"num_tokens": 35393033.0,
|
| 17479 |
+
"step": 9705
|
| 17480 |
+
},
|
| 17481 |
+
{
|
| 17482 |
+
"epoch": 74.6923076923077,
|
| 17483 |
+
"grad_norm": 0.0,
|
| 17484 |
+
"learning_rate": 1.455e-06,
|
| 17485 |
+
"loss": 1.7162,
|
| 17486 |
+
"mean_token_accuracy": 0.6562795639038086,
|
| 17487 |
+
"num_tokens": 35411155.0,
|
| 17488 |
+
"step": 9710
|
| 17489 |
}
|
| 17490 |
],
|
| 17491 |
"logging_steps": 5,
|
|
|
|
| 17505 |
"attributes": {}
|
| 17506 |
}
|
| 17507 |
},
|
| 17508 |
+
"total_flos": 1.7957754721640448e+18,
|
| 17509 |
"train_batch_size": 4,
|
| 17510 |
"trial_name": null,
|
| 17511 |
"trial_params": null
|