TachyHealthResearch
commited on
Commit
•
cb23276
1
Parent(s):
877a76f
Training in progress, step 50, 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 sha256:082e0f65d9408d58de78384d26e1aad492bc230933c9354dc36177931ee5be37
|
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 sha256:1303a139905c4f79955959992b09a87c0185864715be3314300530474ce995a8
|
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:fb666093d54c6ea7061dd8f6ce0161fe9011e0b6517a61dc248791ee21e8e12d
|
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:ff3806b6ededc075c4c89012dc49cff3604a5f3bc56562d72a0f71b6ec838696
|
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,
|
@@ -247,13 +247,73 @@
|
|
247 |
"learning_rate": 0.0001263157894736842,
|
248 |
"loss": 1.4438,
|
249 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 1,
|
253 |
"max_steps": 100,
|
254 |
"num_train_epochs": 1,
|
255 |
"save_steps": 10,
|
256 |
-
"total_flos":
|
257 |
"trial_name": null,
|
258 |
"trial_params": null
|
259 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.02,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
247 |
"learning_rate": 0.0001263157894736842,
|
248 |
"loss": 1.4438,
|
249 |
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.02,
|
253 |
+
"learning_rate": 0.00012421052631578949,
|
254 |
+
"loss": 1.4265,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.02,
|
259 |
+
"learning_rate": 0.00012210526315789474,
|
260 |
+
"loss": 1.6946,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.02,
|
265 |
+
"learning_rate": 0.00012,
|
266 |
+
"loss": 1.9664,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.02,
|
271 |
+
"learning_rate": 0.00011789473684210525,
|
272 |
+
"loss": 1.7266,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.02,
|
277 |
+
"learning_rate": 0.00011578947368421053,
|
278 |
+
"loss": 1.8053,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.02,
|
283 |
+
"learning_rate": 0.0001136842105263158,
|
284 |
+
"loss": 1.3368,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.02,
|
289 |
+
"learning_rate": 0.00011157894736842105,
|
290 |
+
"loss": 1.8476,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.02,
|
295 |
+
"learning_rate": 0.00010947368421052633,
|
296 |
+
"loss": 1.5476,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.02,
|
301 |
+
"learning_rate": 0.00010736842105263158,
|
302 |
+
"loss": 1.7867,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.02,
|
307 |
+
"learning_rate": 0.00010526315789473685,
|
308 |
+
"loss": 1.4282,
|
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": 3055618882191360.0,
|
317 |
"trial_name": null,
|
318 |
"trial_params": null
|
319 |
}
|