Training in progress, step 9700, 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:b1c3c28451b9d1c4eb7f6d1f067c9fcefda8138ae7b1f5b381bc963cfa785b03
|
| 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 sha256:81fc6d3a837a14009ff453fa6ffb9315f56e8efdffe833a769769683941286b1
|
| 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:c5a2c77bebf5d19c49e0b6a254cebb494699e1c350e590198f908a9999214c53
|
| 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 sha256:50fe0a90981832fe0e1e32782a114c4487fbad01a5b28349058e8f9db694967b
|
| 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": 19.
|
| 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,
|
|
@@ -831,6 +831,13 @@
|
|
| 831 |
"learning_rate": 3.6e-05,
|
| 832 |
"loss": 1.2228,
|
| 833 |
"step": 9600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 834 |
}
|
| 835 |
],
|
| 836 |
"logging_steps": 100,
|
|
@@ -850,7 +857,7 @@
|
|
| 850 |
"attributes": {}
|
| 851 |
}
|
| 852 |
},
|
| 853 |
-
"total_flos": 1.
|
| 854 |
"train_batch_size": 8,
|
| 855 |
"trial_name": null,
|
| 856 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.39696922355882,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 831 |
"learning_rate": 3.6e-05,
|
| 832 |
"loss": 1.2228,
|
| 833 |
"step": 9600
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 19.39696922355882,
|
| 837 |
+
"grad_norm": 0.24351443350315094,
|
| 838 |
+
"learning_rate": 3.5333333333333336e-05,
|
| 839 |
+
"loss": 1.227,
|
| 840 |
+
"step": 9700
|
| 841 |
}
|
| 842 |
],
|
| 843 |
"logging_steps": 100,
|
|
|
|
| 857 |
"attributes": {}
|
| 858 |
}
|
| 859 |
},
|
| 860 |
+
"total_flos": 1.513909822471694e+19,
|
| 861 |
"train_batch_size": 8,
|
| 862 |
"trial_name": null,
|
| 863 |
"trial_params": null
|