Training in progress, step 8110, 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:bbe02b84b87c40169fe4a080c8601a16a548cf7a8ee766b99a6696968721090a
|
| 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 sha256:862aa47faa93adb7b0dda7f992d6930bd7493195890aede2ed56062b73b48137
|
| 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 sha256:4e53e3c82f0b16f9ad61a19e9de3e40fb4efd56bbfdcdb6ad4219934a0b5769f
|
| 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": 62.
|
| 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,
|
|
@@ -14588,6 +14588,24 @@
|
|
| 14588 |
"mean_token_accuracy": 0.6537641167640686,
|
| 14589 |
"num_tokens": 29539856.0,
|
| 14590 |
"step": 8100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14591 |
}
|
| 14592 |
],
|
| 14593 |
"logging_steps": 5,
|
|
@@ -14607,7 +14625,7 @@
|
|
| 14607 |
"attributes": {}
|
| 14608 |
}
|
| 14609 |
},
|
| 14610 |
-
"total_flos": 1.
|
| 14611 |
"train_batch_size": 4,
|
| 14612 |
"trial_name": null,
|
| 14613 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8110,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14588 |
"mean_token_accuracy": 0.6537641167640686,
|
| 14589 |
"num_tokens": 29539856.0,
|
| 14590 |
"step": 8100
|
| 14591 |
+
},
|
| 14592 |
+
{
|
| 14593 |
+
"epoch": 62.34615384615385,
|
| 14594 |
+
"grad_norm": 0.0,
|
| 14595 |
+
"learning_rate": 9.48e-06,
|
| 14596 |
+
"loss": 1.7475,
|
| 14597 |
+
"mean_token_accuracy": 0.6510567903518677,
|
| 14598 |
+
"num_tokens": 29557912.0,
|
| 14599 |
+
"step": 8105
|
| 14600 |
+
},
|
| 14601 |
+
{
|
| 14602 |
+
"epoch": 62.38461538461539,
|
| 14603 |
+
"grad_norm": 0.0,
|
| 14604 |
+
"learning_rate": 9.455e-06,
|
| 14605 |
+
"loss": 1.7125,
|
| 14606 |
+
"mean_token_accuracy": 0.6581447750329972,
|
| 14607 |
+
"num_tokens": 29576445.0,
|
| 14608 |
+
"step": 8110
|
| 14609 |
}
|
| 14610 |
],
|
| 14611 |
"logging_steps": 5,
|
|
|
|
| 14625 |
"attributes": {}
|
| 14626 |
}
|
| 14627 |
},
|
| 14628 |
+
"total_flos": 1.4996337872663347e+18,
|
| 14629 |
"train_batch_size": 4,
|
| 14630 |
"trial_name": null,
|
| 14631 |
"trial_params": null
|