Training in progress, step 3700, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdefd00b4614a894a24fa2cfa06d76750152f1c44ab5579b97b4f0875a23ec97
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a178045f266abc523d04a343fee6a7a40098a0745bea9b8113b74532437240c
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0404822d734f61a0e1c3549969500c55614ad5d6b3b266b89bf054bb137ac04
|
| 3 |
size 14645
|
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 sha256:60b0c73069fab3f25c1faf61b3aeaf39b8cbbccb4265c070816385bb7cb2238f
|
| 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": 0.
|
| 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,
|
|
@@ -3708,6 +3708,16 @@
|
|
| 3708 |
"mean_token_accuracy": 0.7530387908220291,
|
| 3709 |
"num_tokens": 17191263.0,
|
| 3710 |
"step": 3690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3711 |
}
|
| 3712 |
],
|
| 3713 |
"logging_steps": 10,
|
|
@@ -3727,7 +3737,7 @@
|
|
| 3727 |
"attributes": {}
|
| 3728 |
}
|
| 3729 |
},
|
| 3730 |
-
"total_flos": 8.
|
| 3731 |
"train_batch_size": 4,
|
| 3732 |
"trial_name": null,
|
| 3733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7893333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3708 |
"mean_token_accuracy": 0.7530387908220291,
|
| 3709 |
"num_tokens": 17191263.0,
|
| 3710 |
"step": 3690
|
| 3711 |
+
},
|
| 3712 |
+
{
|
| 3713 |
+
"entropy": 0.8815206326544285,
|
| 3714 |
+
"epoch": 0.7893333333333333,
|
| 3715 |
+
"grad_norm": 0.28048619627952576,
|
| 3716 |
+
"learning_rate": 6.92061020966232e-05,
|
| 3717 |
+
"loss": 0.9586901664733887,
|
| 3718 |
+
"mean_token_accuracy": 0.7787635132670403,
|
| 3719 |
+
"num_tokens": 17235554.0,
|
| 3720 |
+
"step": 3700
|
| 3721 |
}
|
| 3722 |
],
|
| 3723 |
"logging_steps": 10,
|
|
|
|
| 3737 |
"attributes": {}
|
| 3738 |
}
|
| 3739 |
},
|
| 3740 |
+
"total_flos": 8.161667352998707e+16,
|
| 3741 |
"train_batch_size": 4,
|
| 3742 |
"trial_name": null,
|
| 3743 |
"trial_params": null
|