Training in progress, step 44, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b8464ada8d2a8b5111340ca8eaf88c635189447671fcd01e2a5c1095cb92de8
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ced9c98bc6b597276e3f1f70f6afc5f80ffcb7a0f610f9e798b2d50799a7756c
|
3 |
size 37430836
|
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:c134361f6786d848c90ab6fe56c7855e1e48d2d09ca3556b281b17aa210f9d50
|
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": 0.
|
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,
|
@@ -308,6 +308,13 @@
|
|
308 |
"learning_rate": 8.6e-05,
|
309 |
"loss": 1.4127,
|
310 |
"step": 43
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
311 |
}
|
312 |
],
|
313 |
"logging_steps": 1,
|
@@ -327,7 +334,7 @@
|
|
327 |
"attributes": {}
|
328 |
}
|
329 |
},
|
330 |
-
"total_flos": 5.
|
331 |
"train_batch_size": 4,
|
332 |
"trial_name": null,
|
333 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.12071330589849108,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 44,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
308 |
"learning_rate": 8.6e-05,
|
309 |
"loss": 1.4127,
|
310 |
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.12071330589849108,
|
314 |
+
"grad_norm": 0.10291855037212372,
|
315 |
+
"learning_rate": 8.800000000000001e-05,
|
316 |
+
"loss": 1.4187,
|
317 |
+
"step": 44
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 1,
|
|
|
334 |
"attributes": {}
|
335 |
}
|
336 |
},
|
337 |
+
"total_flos": 5.435040946301338e+16,
|
338 |
"train_batch_size": 4,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|