Training in progress, step 9750, 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 sha256:6697f94d7588cb8d3d816e1da0ba6463083aac5a5a535c6b135a4a98c803ffd5
|
| 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:b297adcf1d2c56a0bb10292b13bd4b80441a737a7dde796b436d54d59963b5e5
|
| 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 sha256:718fc7f0386e4d43c4ef8d7d0f4174cf5dc5b19d5c7c613ad6ebdb275a5c737e
|
| 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,
|
|
@@ -17540,6 +17540,24 @@
|
|
| 17540 |
"mean_token_accuracy": 0.6560095697641373,
|
| 17541 |
"num_tokens": 35521179.0,
|
| 17542 |
"step": 9740
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17543 |
}
|
| 17544 |
],
|
| 17545 |
"logging_steps": 5,
|
|
@@ -17559,7 +17577,7 @@
|
|
| 17559 |
"attributes": {}
|
| 17560 |
}
|
| 17561 |
},
|
| 17562 |
-
"total_flos": 1.
|
| 17563 |
"train_batch_size": 4,
|
| 17564 |
"trial_name": null,
|
| 17565 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 75.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9750,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17540 |
"mean_token_accuracy": 0.6560095697641373,
|
| 17541 |
"num_tokens": 35521179.0,
|
| 17542 |
"step": 9740
|
| 17543 |
+
},
|
| 17544 |
+
{
|
| 17545 |
+
"epoch": 74.96153846153847,
|
| 17546 |
+
"grad_norm": 0.0,
|
| 17547 |
+
"learning_rate": 1.28e-06,
|
| 17548 |
+
"loss": 1.7289,
|
| 17549 |
+
"mean_token_accuracy": 0.6569119274616242,
|
| 17550 |
+
"num_tokens": 35539684.0,
|
| 17551 |
+
"step": 9745
|
| 17552 |
+
},
|
| 17553 |
+
{
|
| 17554 |
+
"epoch": 75.0,
|
| 17555 |
+
"grad_norm": 0.0,
|
| 17556 |
+
"learning_rate": 1.255e-06,
|
| 17557 |
+
"loss": 1.7786,
|
| 17558 |
+
"mean_token_accuracy": 0.6401764988899231,
|
| 17559 |
+
"num_tokens": 35557875.0,
|
| 17560 |
+
"step": 9750
|
| 17561 |
}
|
| 17562 |
],
|
| 17563 |
"logging_steps": 5,
|
|
|
|
| 17577 |
"attributes": {}
|
| 17578 |
}
|
| 17579 |
},
|
| 17580 |
+
"total_flos": 1.8031990323673498e+18,
|
| 17581 |
"train_batch_size": 4,
|
| 17582 |
"trial_name": null,
|
| 17583 |
"trial_params": null
|