Training in progress, step 4690, 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:bdb0b08c69e613af2d1d54680a88a33e0201e2bc4e3a4dbe91677c7e313a5d64
|
| 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 sha256:74780e32301d4deffd3455739db4e1b8f258aa1ca48fc8d5d782a68767fcb64b
|
| 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 sha256:432b323db2ff58cc8a49a52079e9d419b671c4dbd75c616cc5957ddb484611d6
|
| 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": 36.
|
| 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,
|
|
@@ -8432,6 +8432,24 @@
|
|
| 8432 |
"mean_token_accuracy": 0.6355714172124862,
|
| 8433 |
"num_tokens": 17067780.0,
|
| 8434 |
"step": 4680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8435 |
}
|
| 8436 |
],
|
| 8437 |
"logging_steps": 5,
|
|
@@ -8451,7 +8469,7 @@
|
|
| 8451 |
"attributes": {}
|
| 8452 |
}
|
| 8453 |
},
|
| 8454 |
-
"total_flos": 8.
|
| 8455 |
"train_batch_size": 4,
|
| 8456 |
"trial_name": null,
|
| 8457 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8432 |
"mean_token_accuracy": 0.6355714172124862,
|
| 8433 |
"num_tokens": 17067780.0,
|
| 8434 |
"step": 4680
|
| 8435 |
+
},
|
| 8436 |
+
{
|
| 8437 |
+
"epoch": 36.03846153846154,
|
| 8438 |
+
"grad_norm": 0.0,
|
| 8439 |
+
"learning_rate": 2.658e-05,
|
| 8440 |
+
"loss": 1.8764,
|
| 8441 |
+
"mean_token_accuracy": 0.6272640764713288,
|
| 8442 |
+
"num_tokens": 17084927.0,
|
| 8443 |
+
"step": 4685
|
| 8444 |
+
},
|
| 8445 |
+
{
|
| 8446 |
+
"epoch": 36.07692307692308,
|
| 8447 |
+
"grad_norm": 0.0,
|
| 8448 |
+
"learning_rate": 2.6555000000000002e-05,
|
| 8449 |
+
"loss": 1.754,
|
| 8450 |
+
"mean_token_accuracy": 0.6480523020029068,
|
| 8451 |
+
"num_tokens": 17102872.0,
|
| 8452 |
+
"step": 4690
|
| 8453 |
}
|
| 8454 |
],
|
| 8455 |
"logging_steps": 5,
|
|
|
|
| 8469 |
"attributes": {}
|
| 8470 |
}
|
| 8471 |
},
|
| 8472 |
+
"total_flos": 8.668015578832896e+17,
|
| 8473 |
"train_batch_size": 4,
|
| 8474 |
"trial_name": null,
|
| 8475 |
"trial_params": null
|