TachyHealthResearch
commited on
Commit
•
ef9d811
1
Parent(s):
e534833
Training in progress, step 60, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:376a3d27f0b1944494854ef53f3cae507ae395c3d1eb4a9fb04b4918e1482b14
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42545748
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a66101811aa26237703ee0b600450fa3d9faaa7c72ad1d2093f56e124c8dd86
|
3 |
size 42545748
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:babf9cef0f970e1cd241f9533a5b0bc052a39fc9df617e7f31209a9691bd42d1
|
3 |
size 14244
|
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 sha256:87f5541cd8b8cc2355cb28b7b43b87c2e735f1841d8477f8ed4c15392845734c
|
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": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -307,13 +307,73 @@
|
|
307 |
"learning_rate": 0.00010526315789473685,
|
308 |
"loss": 1.5211,
|
309 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
310 |
}
|
311 |
],
|
312 |
"logging_steps": 1,
|
313 |
"max_steps": 100,
|
314 |
"num_train_epochs": 1,
|
315 |
"save_steps": 10,
|
316 |
-
"total_flos":
|
317 |
"trial_name": null,
|
318 |
"trial_params": null
|
319 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.024,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 60,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
307 |
"learning_rate": 0.00010526315789473685,
|
308 |
"loss": 1.5211,
|
309 |
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.02,
|
313 |
+
"learning_rate": 0.00010315789473684211,
|
314 |
+
"loss": 1.8625,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.02,
|
319 |
+
"learning_rate": 0.00010105263157894738,
|
320 |
+
"loss": 1.7274,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.02,
|
325 |
+
"learning_rate": 9.894736842105263e-05,
|
326 |
+
"loss": 1.6251,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.02,
|
331 |
+
"learning_rate": 9.68421052631579e-05,
|
332 |
+
"loss": 1.5311,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.02,
|
337 |
+
"learning_rate": 9.473684210526316e-05,
|
338 |
+
"loss": 1.5397,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.02,
|
343 |
+
"learning_rate": 9.263157894736843e-05,
|
344 |
+
"loss": 1.8251,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.02,
|
349 |
+
"learning_rate": 9.052631578947369e-05,
|
350 |
+
"loss": 1.7583,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.02,
|
355 |
+
"learning_rate": 8.842105263157894e-05,
|
356 |
+
"loss": 1.6476,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.02,
|
361 |
+
"learning_rate": 8.631578947368421e-05,
|
362 |
+
"loss": 1.9871,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.02,
|
367 |
+
"learning_rate": 8.421052631578948e-05,
|
368 |
+
"loss": 1.6805,
|
369 |
+
"step": 60
|
370 |
}
|
371 |
],
|
372 |
"logging_steps": 1,
|
373 |
"max_steps": 100,
|
374 |
"num_train_epochs": 1,
|
375 |
"save_steps": 10,
|
376 |
+
"total_flos": 3532725037301760.0,
|
377 |
"trial_name": null,
|
378 |
"trial_params": null
|
379 |
}
|