Training in progress, step 310, 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 sha256:4d7d6719ff182793ec617cb58fe272426a40e825917e1011470793d8b6d5a94c
|
| 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 sha256:6aa44ab270ae11c61f7b5075e53cab15c660015a30b597673410786591df1ffd
|
| 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:c08cceb79bc7a7db2b28f1f54d653303acd5a65794c237fd537ce777044f6703
|
| 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": 2.
|
| 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,
|
|
@@ -548,6 +548,24 @@
|
|
| 548 |
"mean_token_accuracy": 0.6457105249166488,
|
| 549 |
"num_tokens": 1096433.0,
|
| 550 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 551 |
}
|
| 552 |
],
|
| 553 |
"logging_steps": 5,
|
|
@@ -567,7 +585,7 @@
|
|
| 567 |
"attributes": {}
|
| 568 |
}
|
| 569 |
},
|
| 570 |
-
"total_flos": 5.
|
| 571 |
"train_batch_size": 4,
|
| 572 |
"trial_name": null,
|
| 573 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.3846153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 548 |
"mean_token_accuracy": 0.6457105249166488,
|
| 549 |
"num_tokens": 1096433.0,
|
| 550 |
"step": 300
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.3461538461538463,
|
| 554 |
+
"grad_norm": 0.0,
|
| 555 |
+
"learning_rate": 4.8480000000000003e-05,
|
| 556 |
+
"loss": 1.7599,
|
| 557 |
+
"mean_token_accuracy": 0.6529647082090377,
|
| 558 |
+
"num_tokens": 1114140.0,
|
| 559 |
+
"step": 305
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.3846153846153846,
|
| 563 |
+
"grad_norm": 0.0,
|
| 564 |
+
"learning_rate": 4.8455e-05,
|
| 565 |
+
"loss": 1.7591,
|
| 566 |
+
"mean_token_accuracy": 0.6483295440673829,
|
| 567 |
+
"num_tokens": 1132366.0,
|
| 568 |
+
"step": 310
|
| 569 |
}
|
| 570 |
],
|
| 571 |
"logging_steps": 5,
|
|
|
|
| 585 |
"attributes": {}
|
| 586 |
}
|
| 587 |
},
|
| 588 |
+
"total_flos": 5.737738496016384e+16,
|
| 589 |
"train_batch_size": 4,
|
| 590 |
"trial_name": null,
|
| 591 |
"trial_params": null
|