Training in progress, step 9740, 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 sha256:24b8bb5cee35dd3e35b349dc2c17ac95995d1f1666570909981169c1683c860e
|
| 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:d3d1ed23ac4fa6e254c09d5720ecf1f8b228d6da7d130ef4858c5e4fd72959ad
|
| 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 sha256:1125130ddd3bb07d5ab43045b8084a893f6f2ce15a864302fcb34b0b57ae62a4
|
| 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,
|
|
@@ -17522,6 +17522,24 @@
|
|
| 17522 |
"mean_token_accuracy": 0.6479380965232849,
|
| 17523 |
"num_tokens": 35484088.0,
|
| 17524 |
"step": 9730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17525 |
}
|
| 17526 |
],
|
| 17527 |
"logging_steps": 5,
|
|
@@ -17541,7 +17559,7 @@
|
|
| 17541 |
"attributes": {}
|
| 17542 |
}
|
| 17543 |
},
|
| 17544 |
-
"total_flos": 1.
|
| 17545 |
"train_batch_size": 4,
|
| 17546 |
"trial_name": null,
|
| 17547 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17522 |
"mean_token_accuracy": 0.6479380965232849,
|
| 17523 |
"num_tokens": 35484088.0,
|
| 17524 |
"step": 9730
|
| 17525 |
+
},
|
| 17526 |
+
{
|
| 17527 |
+
"epoch": 74.88461538461539,
|
| 17528 |
+
"grad_norm": 0.0,
|
| 17529 |
+
"learning_rate": 1.33e-06,
|
| 17530 |
+
"loss": 1.747,
|
| 17531 |
+
"mean_token_accuracy": 0.6452481150627136,
|
| 17532 |
+
"num_tokens": 35502027.0,
|
| 17533 |
+
"step": 9735
|
| 17534 |
+
},
|
| 17535 |
+
{
|
| 17536 |
+
"epoch": 74.92307692307692,
|
| 17537 |
+
"grad_norm": 0.0,
|
| 17538 |
+
"learning_rate": 1.3050000000000002e-06,
|
| 17539 |
+
"loss": 1.7069,
|
| 17540 |
+
"mean_token_accuracy": 0.6560095697641373,
|
| 17541 |
+
"num_tokens": 35521179.0,
|
| 17542 |
+
"step": 9740
|
| 17543 |
}
|
| 17544 |
],
|
| 17545 |
"logging_steps": 5,
|
|
|
|
| 17559 |
"attributes": {}
|
| 17560 |
}
|
| 17561 |
},
|
| 17562 |
+
"total_flos": 1.8013697378235187e+18,
|
| 17563 |
"train_batch_size": 4,
|
| 17564 |
"trial_name": null,
|
| 17565 |
"trial_params": null
|