Training in progress, step 46, 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 sha256:05c236a1ea4dddfe2de5f0855d3f57f1dedf8789ac25506fb8f4b14220cd9a42
|
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 sha256:5ae6d6793db8aa8323b404800b1a6f07c8ee81be887e82712bef5c9850c795f9
|
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 sha256:6cce1fa749e8c9785e750267fbe974fa1807d0eb51698b918a4a2f64606f39dc
|
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,
|
@@ -315,6 +315,20 @@
|
|
315 |
"learning_rate": 8.800000000000001e-05,
|
316 |
"loss": 1.4187,
|
317 |
"step": 44
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 1,
|
@@ -334,7 +348,7 @@
|
|
334 |
"attributes": {}
|
335 |
}
|
336 |
},
|
337 |
-
"total_flos": 5.
|
338 |
"train_batch_size": 4,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1262002743484225,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 46,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
315 |
"learning_rate": 8.800000000000001e-05,
|
316 |
"loss": 1.4187,
|
317 |
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.12345679012345678,
|
321 |
+
"grad_norm": 0.10925430059432983,
|
322 |
+
"learning_rate": 9e-05,
|
323 |
+
"loss": 1.3476,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.1262002743484225,
|
328 |
+
"grad_norm": 0.10825473070144653,
|
329 |
+
"learning_rate": 9.200000000000001e-05,
|
330 |
+
"loss": 1.4427,
|
331 |
+
"step": 46
|
332 |
}
|
333 |
],
|
334 |
"logging_steps": 1,
|
|
|
348 |
"attributes": {}
|
349 |
}
|
350 |
},
|
351 |
+
"total_flos": 5.688683838890803e+16,
|
352 |
"train_batch_size": 4,
|
353 |
"trial_name": null,
|
354 |
"trial_params": null
|