Training in progress, step 3410, 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 sha256:7521f37bee0ee52e735bad9c72319f217d014fb444f098ce64f95ebb37c3fdaa
|
| 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:af07ffe897abfd723adcd9431b56fcace89cfee5544c962c16f32d2914255771
|
| 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 sha256:71a98c890f0dde5e487a2c8dd6730156298c761e78de84e99519359ad62979ef
|
| 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 sha256:01ebfa5ecb9b488cde9cea210c2835fe825c038d4fa1cf731b310ebe9642e0e7
|
| 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,
|
|
@@ -3418,6 +3418,16 @@
|
|
| 3418 |
"mean_token_accuracy": 0.7544682174921036,
|
| 3419 |
"num_tokens": 15837848.0,
|
| 3420 |
"step": 3400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3421 |
}
|
| 3422 |
],
|
| 3423 |
"logging_steps": 10,
|
|
@@ -3437,7 +3447,7 @@
|
|
| 3437 |
"attributes": {}
|
| 3438 |
}
|
| 3439 |
},
|
| 3440 |
-
"total_flos": 7.
|
| 3441 |
"train_batch_size": 4,
|
| 3442 |
"trial_name": null,
|
| 3443 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7274666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3418 |
"mean_token_accuracy": 0.7544682174921036,
|
| 3419 |
"num_tokens": 15837848.0,
|
| 3420 |
"step": 3400
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"entropy": 0.9885091617703438,
|
| 3424 |
+
"epoch": 0.7274666666666667,
|
| 3425 |
+
"grad_norm": 0.31231454014778137,
|
| 3426 |
+
"learning_rate": 7.373566042999559e-05,
|
| 3427 |
+
"loss": 1.0966137886047362,
|
| 3428 |
+
"mean_token_accuracy": 0.7566501721739769,
|
| 3429 |
+
"num_tokens": 15885904.0,
|
| 3430 |
+
"step": 3410
|
| 3431 |
}
|
| 3432 |
],
|
| 3433 |
"logging_steps": 10,
|
|
|
|
| 3447 |
"attributes": {}
|
| 3448 |
}
|
| 3449 |
},
|
| 3450 |
+
"total_flos": 7.52470126576681e+16,
|
| 3451 |
"train_batch_size": 4,
|
| 3452 |
"trial_name": null,
|
| 3453 |
"trial_params": null
|