Training in progress, step 2070, 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:c98cfa542d6d3a24bd0ddb225a1edb2bdf2f8d2a832e2ba2910b4ef082d3b91b
|
| 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:fd5802a98cfa3dae427cd06a55d54a5313692897e70ae60280bd063f35519239
|
| 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 sha256:6046e55f47fc9bce8ac723ae2ac069ee62085b166ac5776cdd39bbf5e4509b99
|
| 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": 15.
|
| 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,
|
|
@@ -3716,6 +3716,24 @@
|
|
| 3716 |
"mean_token_accuracy": 0.648233824968338,
|
| 3717 |
"num_tokens": 7511123.0,
|
| 3718 |
"step": 2060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3719 |
}
|
| 3720 |
],
|
| 3721 |
"logging_steps": 5,
|
|
@@ -3735,7 +3753,7 @@
|
|
| 3735 |
"attributes": {}
|
| 3736 |
}
|
| 3737 |
},
|
| 3738 |
-
"total_flos": 3.
|
| 3739 |
"train_batch_size": 4,
|
| 3740 |
"trial_name": null,
|
| 3741 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2070,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3716 |
"mean_token_accuracy": 0.648233824968338,
|
| 3717 |
"num_tokens": 7511123.0,
|
| 3718 |
"step": 2060
|
| 3719 |
+
},
|
| 3720 |
+
{
|
| 3721 |
+
"epoch": 15.884615384615385,
|
| 3722 |
+
"grad_norm": 0.0,
|
| 3723 |
+
"learning_rate": 3.968e-05,
|
| 3724 |
+
"loss": 1.6579,
|
| 3725 |
+
"mean_token_accuracy": 0.6663879871368408,
|
| 3726 |
+
"num_tokens": 7530727.0,
|
| 3727 |
+
"step": 2065
|
| 3728 |
+
},
|
| 3729 |
+
{
|
| 3730 |
+
"epoch": 15.923076923076923,
|
| 3731 |
+
"grad_norm": 0.0,
|
| 3732 |
+
"learning_rate": 3.9655000000000006e-05,
|
| 3733 |
+
"loss": 1.7077,
|
| 3734 |
+
"mean_token_accuracy": 0.6618927121162415,
|
| 3735 |
+
"num_tokens": 7549141.0,
|
| 3736 |
+
"step": 2070
|
| 3737 |
}
|
| 3738 |
],
|
| 3739 |
"logging_steps": 5,
|
|
|
|
| 3753 |
"attributes": {}
|
| 3754 |
}
|
| 3755 |
},
|
| 3756 |
+
"total_flos": 3.8248372049412096e+17,
|
| 3757 |
"train_batch_size": 4,
|
| 3758 |
"trial_name": null,
|
| 3759 |
"trial_params": null
|