Training in progress, step 3310, 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:ec4b760fa88a8a9c39191832e0d980685bfeefaedaa872e60a2c1422b3ec9d16
|
| 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 sha256:1a9a9369a40bddfc3cf16ae2ea17b8bc75bfe3848c778aa0b1627d423860a402
|
| 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 sha256:99a44504e68e0b1a4d0338b40097b145935a007bbf9a05499a56ef9cff265d18
|
| 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 sha256:44fa04db905ec84c33ecbd287477dc443ddf610f97d4f6d15d460da3be8f9a6f
|
| 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,
|
|
@@ -3318,6 +3318,16 @@
|
|
| 3318 |
"mean_token_accuracy": 0.7683326050639152,
|
| 3319 |
"num_tokens": 15350117.0,
|
| 3320 |
"step": 3300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3321 |
}
|
| 3322 |
],
|
| 3323 |
"logging_steps": 10,
|
|
@@ -3337,7 +3347,7 @@
|
|
| 3337 |
"attributes": {}
|
| 3338 |
}
|
| 3339 |
},
|
| 3340 |
-
"total_flos": 7.
|
| 3341 |
"train_batch_size": 4,
|
| 3342 |
"trial_name": null,
|
| 3343 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7061333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3318 |
"mean_token_accuracy": 0.7683326050639152,
|
| 3319 |
"num_tokens": 15350117.0,
|
| 3320 |
"step": 3300
|
| 3321 |
+
},
|
| 3322 |
+
{
|
| 3323 |
+
"entropy": 1.0591608263552188,
|
| 3324 |
+
"epoch": 0.7061333333333333,
|
| 3325 |
+
"grad_norm": 0.28637412190437317,
|
| 3326 |
+
"learning_rate": 7.524441010181889e-05,
|
| 3327 |
+
"loss": 1.1826082229614259,
|
| 3328 |
+
"mean_token_accuracy": 0.7397180199623108,
|
| 3329 |
+
"num_tokens": 15404947.0,
|
| 3330 |
+
"step": 3310
|
| 3331 |
}
|
| 3332 |
],
|
| 3333 |
"logging_steps": 10,
|
|
|
|
| 3347 |
"attributes": {}
|
| 3348 |
}
|
| 3349 |
},
|
| 3350 |
+
"total_flos": 7.296998380031386e+16,
|
| 3351 |
"train_batch_size": 4,
|
| 3352 |
"trial_name": null,
|
| 3353 |
"trial_params": null
|