Training in progress, step 9400, 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 sha256:18610916b9c673dab5c6882b780a62845c873d2c799ed874ab52e599ac3bb2da
|
| 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:ffa99dfca11d28940b83257f420a8866ccecd954b7d059a5ef4ecb1a47de2c9b
|
| 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 sha256:48b1f5cb0a7cc9995b5c483d304c23830306a1fc4c4676dff3bd5ac5b73c09c1
|
| 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 sha256:320edc62b9a77cb6db46c18993bf705328fc5437b8f6124a25ea16d34aae731c
|
| 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": 18.
|
| 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,
|
|
@@ -802,6 +802,13 @@
|
|
| 802 |
"learning_rate": 3.8e-05,
|
| 803 |
"loss": 1.2308,
|
| 804 |
"step": 9300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 805 |
}
|
| 806 |
],
|
| 807 |
"logging_steps": 100,
|
|
@@ -821,7 +828,7 @@
|
|
| 821 |
"attributes": {}
|
| 822 |
}
|
| 823 |
},
|
| 824 |
-
"total_flos": 1.
|
| 825 |
"train_batch_size": 8,
|
| 826 |
"trial_name": null,
|
| 827 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.79706295891267,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 802 |
"learning_rate": 3.8e-05,
|
| 803 |
"loss": 1.2308,
|
| 804 |
"step": 9300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 18.79706295891267,
|
| 808 |
+
"grad_norm": 0.23792578279972076,
|
| 809 |
+
"learning_rate": 3.733333333333334e-05,
|
| 810 |
+
"loss": 1.2278,
|
| 811 |
+
"step": 9400
|
| 812 |
}
|
| 813 |
],
|
| 814 |
"logging_steps": 100,
|
|
|
|
| 828 |
"attributes": {}
|
| 829 |
}
|
| 830 |
},
|
| 831 |
+
"total_flos": 1.4670882468022714e+19,
|
| 832 |
"train_batch_size": 8,
|
| 833 |
"trial_name": null,
|
| 834 |
"trial_params": null
|