Training in progress, step 3910, 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:a1d7c269c32900ab26717893c358e756312092e54d9c7f42c659539c25895e2f
|
| 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 sha256:21e1085347755db71db31272a8b516abd07105fa3da23e9cc2236f4611a34f80
|
| 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 sha256:90b915d9104cea912ea8aa11bce60a0685a11c2b45f7490dcf7595c6622c4492
|
| 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:d9e2df9fcf28701322c4d0660ba950d77c113d36864c915ecba21ae3b2829ee1
|
| 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,
|
|
@@ -3918,6 +3918,16 @@
|
|
| 3918 |
"mean_token_accuracy": 0.7520590081810952,
|
| 3919 |
"num_tokens": 18184374.0,
|
| 3920 |
"step": 3900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3921 |
}
|
| 3922 |
],
|
| 3923 |
"logging_steps": 10,
|
|
@@ -3937,7 +3947,7 @@
|
|
| 3937 |
"attributes": {}
|
| 3938 |
}
|
| 3939 |
},
|
| 3940 |
-
"total_flos": 8.
|
| 3941 |
"train_batch_size": 4,
|
| 3942 |
"trial_name": null,
|
| 3943 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8341333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3918 |
"mean_token_accuracy": 0.7520590081810952,
|
| 3919 |
"num_tokens": 18184374.0,
|
| 3920 |
"step": 3900
|
| 3921 |
+
},
|
| 3922 |
+
{
|
| 3923 |
+
"entropy": 1.0141760632395744,
|
| 3924 |
+
"epoch": 0.8341333333333333,
|
| 3925 |
+
"grad_norm": 0.29730224609375,
|
| 3926 |
+
"learning_rate": 6.580266813050187e-05,
|
| 3927 |
+
"loss": 1.107116985321045,
|
| 3928 |
+
"mean_token_accuracy": 0.7563492476940155,
|
| 3929 |
+
"num_tokens": 18226039.0,
|
| 3930 |
+
"step": 3910
|
| 3931 |
}
|
| 3932 |
],
|
| 3933 |
"logging_steps": 10,
|
|
|
|
| 3947 |
"attributes": {}
|
| 3948 |
}
|
| 3949 |
},
|
| 3950 |
+
"total_flos": 8.627964868946534e+16,
|
| 3951 |
"train_batch_size": 4,
|
| 3952 |
"trial_name": null,
|
| 3953 |
"trial_params": null
|