Training in progress, step 9770, 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 sha256:644d6aed8ec8b3e9649d816a5ba29b08aadffa19fdea801f29494d540ca86531
|
| 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 sha256:64a1ef3351de179e130a5b1f1ab5592069f16af460be9237f03954c9ad2187e6
|
| 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:e2b83dacdbeed6e1d9807be7008117830f0a1c8871fb682eb98bddb546ccf753
|
| 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": 75.
|
| 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,
|
|
@@ -17576,6 +17576,24 @@
|
|
| 17576 |
"mean_token_accuracy": 0.6659580796957016,
|
| 17577 |
"num_tokens": 35594809.0,
|
| 17578 |
"step": 9760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17579 |
}
|
| 17580 |
],
|
| 17581 |
"logging_steps": 5,
|
|
@@ -17595,7 +17613,7 @@
|
|
| 17595 |
"attributes": {}
|
| 17596 |
}
|
| 17597 |
},
|
| 17598 |
-
"total_flos": 1.
|
| 17599 |
"train_batch_size": 4,
|
| 17600 |
"trial_name": null,
|
| 17601 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 75.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17576 |
"mean_token_accuracy": 0.6659580796957016,
|
| 17577 |
"num_tokens": 35594809.0,
|
| 17578 |
"step": 9760
|
| 17579 |
+
},
|
| 17580 |
+
{
|
| 17581 |
+
"epoch": 75.11538461538461,
|
| 17582 |
+
"grad_norm": 0.0,
|
| 17583 |
+
"learning_rate": 1.18e-06,
|
| 17584 |
+
"loss": 1.7825,
|
| 17585 |
+
"mean_token_accuracy": 0.6393451571464539,
|
| 17586 |
+
"num_tokens": 35612932.0,
|
| 17587 |
+
"step": 9765
|
| 17588 |
+
},
|
| 17589 |
+
{
|
| 17590 |
+
"epoch": 75.15384615384616,
|
| 17591 |
+
"grad_norm": 0.0,
|
| 17592 |
+
"learning_rate": 1.155e-06,
|
| 17593 |
+
"loss": 1.8061,
|
| 17594 |
+
"mean_token_accuracy": 0.6380451053380967,
|
| 17595 |
+
"num_tokens": 35630549.0,
|
| 17596 |
+
"step": 9770
|
| 17597 |
}
|
| 17598 |
],
|
| 17599 |
"logging_steps": 5,
|
|
|
|
| 17613 |
"attributes": {}
|
| 17614 |
}
|
| 17615 |
},
|
| 17616 |
+
"total_flos": 1.8068863604804813e+18,
|
| 17617 |
"train_batch_size": 4,
|
| 17618 |
"trial_name": null,
|
| 17619 |
"trial_params": null
|