Training in progress, step 4770, 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:ebe86bb2dbf66b51d23c81b2a56e96938f77043aab7fded722131f83e2378f3c
|
| 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:d4f8f22f71b8c8c0674ba41e2b236401d411312e473a7c91b0b8896e266cdcd4
|
| 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 sha256:64e7ec414d47e133d36508162e843d09327a41aa39316357a65c531e2cc83ed7
|
| 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,
|
|
@@ -8576,6 +8576,24 @@
|
|
| 8576 |
"mean_token_accuracy": 0.6604384332895279,
|
| 8577 |
"num_tokens": 17356798.0,
|
| 8578 |
"step": 4760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8579 |
}
|
| 8580 |
],
|
| 8581 |
"logging_steps": 5,
|
|
@@ -8595,7 +8613,7 @@
|
|
| 8595 |
"attributes": {}
|
| 8596 |
}
|
| 8597 |
},
|
| 8598 |
-
"total_flos": 8.
|
| 8599 |
"train_batch_size": 4,
|
| 8600 |
"trial_name": null,
|
| 8601 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8576 |
"mean_token_accuracy": 0.6604384332895279,
|
| 8577 |
"num_tokens": 17356798.0,
|
| 8578 |
"step": 4760
|
| 8579 |
+
},
|
| 8580 |
+
{
|
| 8581 |
+
"epoch": 36.65384615384615,
|
| 8582 |
+
"grad_norm": 0.0,
|
| 8583 |
+
"learning_rate": 2.618e-05,
|
| 8584 |
+
"loss": 1.7414,
|
| 8585 |
+
"mean_token_accuracy": 0.6457662045955658,
|
| 8586 |
+
"num_tokens": 17375411.0,
|
| 8587 |
+
"step": 4765
|
| 8588 |
+
},
|
| 8589 |
+
{
|
| 8590 |
+
"epoch": 36.69230769230769,
|
| 8591 |
+
"grad_norm": 0.0,
|
| 8592 |
+
"learning_rate": 2.6155000000000003e-05,
|
| 8593 |
+
"loss": 1.7765,
|
| 8594 |
+
"mean_token_accuracy": 0.6472298890352249,
|
| 8595 |
+
"num_tokens": 17392790.0,
|
| 8596 |
+
"step": 4770
|
| 8597 |
}
|
| 8598 |
],
|
| 8599 |
"logging_steps": 5,
|
|
|
|
| 8613 |
"attributes": {}
|
| 8614 |
}
|
| 8615 |
},
|
| 8616 |
+
"total_flos": 8.813812942076314e+17,
|
| 8617 |
"train_batch_size": 4,
|
| 8618 |
"trial_name": null,
|
| 8619 |
"trial_params": null
|