Training in progress, step 3920, 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 sha256:31bc93060aa1184b691124bc90c3e818b4bbd4ceef85e3743663db1a5501317d
|
| 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 sha256:2ac11df89d5d5087ab54baed219bece04e40d4301762cc8cc572077525586373
|
| 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 sha256:53766f1a435dd67babc209d7d3d785f039bc193286ba9f0d6820ca9248374731
|
| 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:fcbd0568a27645a5c5a0dce738eb2c9e393d0b3f97651ba1f9a6650098876f4f
|
| 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,
|
|
@@ -3928,6 +3928,16 @@
|
|
| 3928 |
"mean_token_accuracy": 0.7563492476940155,
|
| 3929 |
"num_tokens": 18226039.0,
|
| 3930 |
"step": 3910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3931 |
}
|
| 3932 |
],
|
| 3933 |
"logging_steps": 10,
|
|
@@ -3947,7 +3957,7 @@
|
|
| 3947 |
"attributes": {}
|
| 3948 |
}
|
| 3949 |
},
|
| 3950 |
-
"total_flos": 8.
|
| 3951 |
"train_batch_size": 4,
|
| 3952 |
"trial_name": null,
|
| 3953 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8362666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3920,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3928 |
"mean_token_accuracy": 0.7563492476940155,
|
| 3929 |
"num_tokens": 18226039.0,
|
| 3930 |
"step": 3910
|
| 3931 |
+
},
|
| 3932 |
+
{
|
| 3933 |
+
"entropy": 0.9843406617641449,
|
| 3934 |
+
"epoch": 0.8362666666666667,
|
| 3935 |
+
"grad_norm": 0.26783686876296997,
|
| 3936 |
+
"learning_rate": 6.563837375246463e-05,
|
| 3937 |
+
"loss": 1.0850018501281737,
|
| 3938 |
+
"mean_token_accuracy": 0.7563267104327679,
|
| 3939 |
+
"num_tokens": 18270937.0,
|
| 3940 |
+
"step": 3920
|
| 3941 |
}
|
| 3942 |
],
|
| 3943 |
"logging_steps": 10,
|
|
|
|
| 3957 |
"attributes": {}
|
| 3958 |
}
|
| 3959 |
},
|
| 3960 |
+
"total_flos": 8.650172816914944e+16,
|
| 3961 |
"train_batch_size": 4,
|
| 3962 |
"trial_name": null,
|
| 3963 |
"trial_params": null
|