Training in progress, step 9100, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d7c90571e487fb334037382db8507c6115be80982feeaaa91ad2bdcac2d46ed
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d4f4328a8089ad466f641a46d13158a035af423baab17592ec51ecb1da5b2b8
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd1727f1f6d7bd2d050760a905cb142bf61372c09f8cdf86bf3734b5e54eca2a
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cbbe785930a839cc1e268f2799057dc0c61a4092d8578f57cdb46deb66336f5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -781,6 +781,13 @@
|
|
| 781 |
"eval_samples_per_second": 19.864,
|
| 782 |
"eval_steps_per_second": 2.484,
|
| 783 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 784 |
}
|
| 785 |
],
|
| 786 |
"logging_steps": 100,
|
|
@@ -800,7 +807,7 @@
|
|
| 800 |
"attributes": {}
|
| 801 |
}
|
| 802 |
},
|
| 803 |
-
"total_flos": 1.
|
| 804 |
"train_batch_size": 8,
|
| 805 |
"trial_name": null,
|
| 806 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.19715669426652,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 781 |
"eval_samples_per_second": 19.864,
|
| 782 |
"eval_steps_per_second": 2.484,
|
| 783 |
"step": 9000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 18.19715669426652,
|
| 787 |
+
"grad_norm": 0.21790316700935364,
|
| 788 |
+
"learning_rate": 3.933333333333333e-05,
|
| 789 |
+
"loss": 1.2269,
|
| 790 |
+
"step": 9100
|
| 791 |
}
|
| 792 |
],
|
| 793 |
"logging_steps": 100,
|
|
|
|
| 807 |
"attributes": {}
|
| 808 |
}
|
| 809 |
},
|
| 810 |
+
"total_flos": 1.4202657554458214e+19,
|
| 811 |
"train_batch_size": 8,
|
| 812 |
"trial_name": null,
|
| 813 |
"trial_params": null
|