Training in progress, step 3030, 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:dc1eb5133ed8837d1e30c2f70a93b2aa2ca9f1d7a140be2a665b842fe875f285
|
| 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:c2e1620a8fa4ef083f7bdbdbdd57446b743e9752de8abb63143a8a5d8fe42119
|
| 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 sha256:81bb6f02b68abfb9647aa331813e9069c33123146cefa938ee0407866c2d56ec
|
| 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": 23.
|
| 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,
|
|
@@ -5444,6 +5444,24 @@
|
|
| 5444 |
"mean_token_accuracy": 0.6603679537773133,
|
| 5445 |
"num_tokens": 11013198.0,
|
| 5446 |
"step": 3020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5447 |
}
|
| 5448 |
],
|
| 5449 |
"logging_steps": 5,
|
|
@@ -5463,7 +5481,7 @@
|
|
| 5463 |
"attributes": {}
|
| 5464 |
}
|
| 5465 |
},
|
| 5466 |
-
"total_flos": 5.
|
| 5467 |
"train_batch_size": 4,
|
| 5468 |
"trial_name": null,
|
| 5469 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5444 |
"mean_token_accuracy": 0.6603679537773133,
|
| 5445 |
"num_tokens": 11013198.0,
|
| 5446 |
"step": 3020
|
| 5447 |
+
},
|
| 5448 |
+
{
|
| 5449 |
+
"epoch": 23.26923076923077,
|
| 5450 |
+
"grad_norm": 0.0,
|
| 5451 |
+
"learning_rate": 3.4880000000000005e-05,
|
| 5452 |
+
"loss": 1.6675,
|
| 5453 |
+
"mean_token_accuracy": 0.6619115889072418,
|
| 5454 |
+
"num_tokens": 11032529.0,
|
| 5455 |
+
"step": 3025
|
| 5456 |
+
},
|
| 5457 |
+
{
|
| 5458 |
+
"epoch": 23.307692307692307,
|
| 5459 |
+
"grad_norm": 0.0,
|
| 5460 |
+
"learning_rate": 3.4855000000000004e-05,
|
| 5461 |
+
"loss": 1.7215,
|
| 5462 |
+
"mean_token_accuracy": 0.6535635858774185,
|
| 5463 |
+
"num_tokens": 11051447.0,
|
| 5464 |
+
"step": 3030
|
| 5465 |
}
|
| 5466 |
],
|
| 5467 |
"logging_steps": 5,
|
|
|
|
| 5481 |
"attributes": {}
|
| 5482 |
}
|
| 5483 |
},
|
| 5484 |
+
"total_flos": 5.600664459067392e+17,
|
| 5485 |
"train_batch_size": 4,
|
| 5486 |
"trial_name": null,
|
| 5487 |
"trial_params": null
|