Training in progress, step 9600, 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 sha256:70b621dcc3ac5d925b47fec0d6d73d55aea66480852fb5f616f39316e7708585
|
| 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 sha256:6a94e8b8a1ca08a92ecd64007c7c1f9ff0fd60525ef1b82d62c62cafab95d5cc
|
| 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 sha256:9f034b1e79f7dc777356aa75f5d7cec99bfb39d8084aad2575c3c11a5e7edc9c
|
| 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:b4fe7910d12129bb5672ea223de9d2666e560a1b73e44e6d9e3f27be48c0d179
|
| 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,
|
|
@@ -824,6 +824,13 @@
|
|
| 824 |
"eval_samples_per_second": 19.862,
|
| 825 |
"eval_steps_per_second": 2.484,
|
| 826 |
"step": 9500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 827 |
}
|
| 828 |
],
|
| 829 |
"logging_steps": 100,
|
|
@@ -843,7 +850,7 @@
|
|
| 843 |
"attributes": {}
|
| 844 |
}
|
| 845 |
},
|
| 846 |
-
"total_flos": 1.
|
| 847 |
"train_batch_size": 8,
|
| 848 |
"trial_name": null,
|
| 849 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.19700046867677,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 9600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 824 |
"eval_samples_per_second": 19.862,
|
| 825 |
"eval_steps_per_second": 2.484,
|
| 826 |
"step": 9500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 19.19700046867677,
|
| 830 |
+
"grad_norm": 0.23651447892189026,
|
| 831 |
+
"learning_rate": 3.6e-05,
|
| 832 |
+
"loss": 1.2228,
|
| 833 |
+
"step": 9600
|
| 834 |
}
|
| 835 |
],
|
| 836 |
"logging_steps": 100,
|
|
|
|
| 850 |
"attributes": {}
|
| 851 |
}
|
| 852 |
},
|
| 853 |
+
"total_flos": 1.4983023253528773e+19,
|
| 854 |
"train_batch_size": 8,
|
| 855 |
"trial_name": null,
|
| 856 |
"trial_params": null
|