Training in progress, step 4240, 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 sha256:199931146e9fc447794a5aff4f137aa60dd89c683dc8d65236536c4244b534c5
|
| 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:faf45fe45f8e8924cddf664598f4d7ac1a078c3b62dc3b5455033ed6e3ff5390
|
| 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 sha256:64c38565e21a640a35236eb807d2150384a04f754315e1b1c42f83fb69e0777b
|
| 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": 32.
|
| 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,
|
|
@@ -7622,6 +7622,24 @@
|
|
| 7622 |
"mean_token_accuracy": 0.6617184728384018,
|
| 7623 |
"num_tokens": 15428238.0,
|
| 7624 |
"step": 4230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7625 |
}
|
| 7626 |
],
|
| 7627 |
"logging_steps": 5,
|
|
@@ -7641,7 +7659,7 @@
|
|
| 7641 |
"attributes": {}
|
| 7642 |
}
|
| 7643 |
},
|
| 7644 |
-
"total_flos": 7.
|
| 7645 |
"train_batch_size": 4,
|
| 7646 |
"trial_name": null,
|
| 7647 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7622 |
"mean_token_accuracy": 0.6617184728384018,
|
| 7623 |
"num_tokens": 15428238.0,
|
| 7624 |
"step": 4230
|
| 7625 |
+
},
|
| 7626 |
+
{
|
| 7627 |
+
"epoch": 32.57692307692308,
|
| 7628 |
+
"grad_norm": 0.0,
|
| 7629 |
+
"learning_rate": 2.883e-05,
|
| 7630 |
+
"loss": 1.6847,
|
| 7631 |
+
"mean_token_accuracy": 0.660372993350029,
|
| 7632 |
+
"num_tokens": 15446651.0,
|
| 7633 |
+
"step": 4235
|
| 7634 |
+
},
|
| 7635 |
+
{
|
| 7636 |
+
"epoch": 32.61538461538461,
|
| 7637 |
+
"grad_norm": 0.0,
|
| 7638 |
+
"learning_rate": 2.8805e-05,
|
| 7639 |
+
"loss": 1.8002,
|
| 7640 |
+
"mean_token_accuracy": 0.634194228053093,
|
| 7641 |
+
"num_tokens": 15464761.0,
|
| 7642 |
+
"step": 4240
|
| 7643 |
}
|
| 7644 |
],
|
| 7645 |
"logging_steps": 5,
|
|
|
|
| 7659 |
"attributes": {}
|
| 7660 |
}
|
| 7661 |
},
|
| 7662 |
+
"total_flos": 7.83794043137065e+17,
|
| 7663 |
"train_batch_size": 4,
|
| 7664 |
"trial_name": null,
|
| 7665 |
"trial_params": null
|