Training in progress, step 4680, 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:c5e5b4491b3958a4c1c2a12ddcf424f0fa2150bc78018f756f2be6ef136f513b
|
| 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 sha256:758b06fa258fa57b9be7469ce8d2398f51991a7afdf73042b9efecaab8a4dce7
|
| 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 sha256:350fa586917cfeb068a88efeda176ab8f310aeb60123d0f6d5a31bef00ae7195
|
| 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":
|
| 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,
|
|
@@ -8414,6 +8414,24 @@
|
|
| 8414 |
"mean_token_accuracy": 0.644548413157463,
|
| 8415 |
"num_tokens": 17031126.0,
|
| 8416 |
"step": 4670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8417 |
}
|
| 8418 |
],
|
| 8419 |
"logging_steps": 5,
|
|
@@ -8433,7 +8451,7 @@
|
|
| 8433 |
"attributes": {}
|
| 8434 |
}
|
| 8435 |
},
|
| 8436 |
-
"total_flos": 8.
|
| 8437 |
"train_batch_size": 4,
|
| 8438 |
"trial_name": null,
|
| 8439 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8414 |
"mean_token_accuracy": 0.644548413157463,
|
| 8415 |
"num_tokens": 17031126.0,
|
| 8416 |
"step": 4670
|
| 8417 |
+
},
|
| 8418 |
+
{
|
| 8419 |
+
"epoch": 35.96153846153846,
|
| 8420 |
+
"grad_norm": 0.0,
|
| 8421 |
+
"learning_rate": 2.663e-05,
|
| 8422 |
+
"loss": 1.7045,
|
| 8423 |
+
"mean_token_accuracy": 0.6576229840517044,
|
| 8424 |
+
"num_tokens": 17050110.0,
|
| 8425 |
+
"step": 4675
|
| 8426 |
+
},
|
| 8427 |
+
{
|
| 8428 |
+
"epoch": 36.0,
|
| 8429 |
+
"grad_norm": 0.0,
|
| 8430 |
+
"learning_rate": 2.6605000000000004e-05,
|
| 8431 |
+
"loss": 1.8172,
|
| 8432 |
+
"mean_token_accuracy": 0.6355714172124862,
|
| 8433 |
+
"num_tokens": 17067780.0,
|
| 8434 |
+
"step": 4680
|
| 8435 |
}
|
| 8436 |
],
|
| 8437 |
"logging_steps": 5,
|
|
|
|
| 8451 |
"attributes": {}
|
| 8452 |
}
|
| 8453 |
},
|
| 8454 |
+
"total_flos": 8.650476834339226e+17,
|
| 8455 |
"train_batch_size": 4,
|
| 8456 |
"trial_name": null,
|
| 8457 |
"trial_params": null
|