Training in progress, step 10200, 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:fe9f5b9355b8db7bc844d4e3031b435d60cca05a72974f28ddcf0c1cdedeb52c
|
| 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 sha256:077940cb80fdd31fc90aa9fc4bae0b034b19fcefb6f372fec446cd0d2c3fc714
|
| 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:da5e1b81ea27950ea280ddf70147e146c04a108d7357169b69a8a297466f0b7b
|
| 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 sha256:1285f5cf93b9140780cf82375112adf9f2313e253b41c32248c9302ad6a424ed
|
| 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": 20.
|
| 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,
|
|
@@ -874,6 +874,13 @@
|
|
| 874 |
"learning_rate": 3.266666666666667e-05,
|
| 875 |
"loss": 1.2207,
|
| 876 |
"step": 10100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 877 |
}
|
| 878 |
],
|
| 879 |
"logging_steps": 100,
|
|
@@ -893,7 +900,7 @@
|
|
| 893 |
"attributes": {}
|
| 894 |
}
|
| 895 |
},
|
| 896 |
-
"total_flos": 1.
|
| 897 |
"train_batch_size": 8,
|
| 898 |
"trial_name": null,
|
| 899 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.396812997969068,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 10200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 874 |
"learning_rate": 3.266666666666667e-05,
|
| 875 |
"loss": 1.2207,
|
| 876 |
"step": 10100
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 20.396812997969068,
|
| 880 |
+
"grad_norm": 0.22665788233280182,
|
| 881 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 882 |
+
"loss": 1.2271,
|
| 883 |
+
"step": 10200
|
| 884 |
}
|
| 885 |
],
|
| 886 |
"logging_steps": 100,
|
|
|
|
| 900 |
"attributes": {}
|
| 901 |
}
|
| 902 |
},
|
| 903 |
+
"total_flos": 1.5919463923787497e+19,
|
| 904 |
"train_batch_size": 8,
|
| 905 |
"trial_name": null,
|
| 906 |
"trial_params": null
|