Training in progress, step 8600, 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:d726a72d434504ad6ede6f7e34adc138661be7420bd3138ef49ce1557eddd457
|
| 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 sha256:3fb0f1de537df16c17fa5f216427f79656944ba2867a1161a506bf5f7103b90e
|
| 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 sha256:87620347e7a84d7f3a4ef1b8dcf4f27476c160d8ddd074059d494c741fcbb849
|
| 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:e8a76b42710f80e8f8c73034e18808bb89a3747701d0a669841be17e0523e8c0
|
| 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,
|
|
@@ -738,6 +738,13 @@
|
|
| 738 |
"eval_samples_per_second": 19.879,
|
| 739 |
"eval_steps_per_second": 2.486,
|
| 740 |
"step": 8500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 741 |
}
|
| 742 |
],
|
| 743 |
"logging_steps": 100,
|
|
@@ -757,7 +764,7 @@
|
|
| 757 |
"attributes": {}
|
| 758 |
}
|
| 759 |
},
|
| 760 |
-
"total_flos": 1.
|
| 761 |
"train_batch_size": 8,
|
| 762 |
"trial_name": null,
|
| 763 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 17.197312919856273,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 8600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 738 |
"eval_samples_per_second": 19.879,
|
| 739 |
"eval_steps_per_second": 2.486,
|
| 740 |
"step": 8500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 17.197312919856273,
|
| 744 |
+
"grad_norm": 0.2302340865135193,
|
| 745 |
+
"learning_rate": 4.266666666666667e-05,
|
| 746 |
+
"loss": 1.2303,
|
| 747 |
+
"step": 8600
|
| 748 |
}
|
| 749 |
],
|
| 750 |
"logging_steps": 100,
|
|
|
|
| 764 |
"attributes": {}
|
| 765 |
}
|
| 766 |
},
|
| 767 |
+
"total_flos": 1.3422291855387656e+19,
|
| 768 |
"train_batch_size": 8,
|
| 769 |
"trial_name": null,
|
| 770 |
"trial_params": null
|