TachyHealthResearch
commited on
Commit
·
e712790
1
Parent(s):
f3b2ae1
Training in progress, step 45, 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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd339c762d519f025a02f91f9038f9a73f4a39a83087a2c3e458e39ffb1a1c0c
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63350356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:259dfd28d649cfa0e945d3bf469db65d20e00c520f47c964d923cf55444dc01b
|
3 |
size 63350356
|
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:bd7553ed48fb9af9185475a0992950d3f88e91369c31402fc9b619ffc0bfb053
|
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:ce5711d70d3076072f14e7b99af7bcdd0964855992649ccba3c74a3698371762
|
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 +247,43 @@
|
|
247 |
"learning_rate": 0.00014965986394557826,
|
248 |
"loss": 1.4394,
|
249 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 1,
|
253 |
"max_steps": 150,
|
254 |
"num_train_epochs": 1,
|
255 |
"save_steps": 5,
|
256 |
-
"total_flos":
|
257 |
"trial_name": null,
|
258 |
"trial_params": null
|
259 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.018,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 45,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
247 |
"learning_rate": 0.00014965986394557826,
|
248 |
"loss": 1.4394,
|
249 |
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.02,
|
253 |
+
"learning_rate": 0.00014829931972789117,
|
254 |
+
"loss": 1.4033,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.02,
|
259 |
+
"learning_rate": 0.0001469387755102041,
|
260 |
+
"loss": 1.5887,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.02,
|
265 |
+
"learning_rate": 0.000145578231292517,
|
266 |
+
"loss": 1.8761,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.02,
|
271 |
+
"learning_rate": 0.00014421768707482995,
|
272 |
+
"loss": 1.67,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.02,
|
277 |
+
"learning_rate": 0.00014285714285714287,
|
278 |
+
"loss": 1.8064,
|
279 |
+
"step": 45
|
280 |
}
|
281 |
],
|
282 |
"logging_steps": 1,
|
283 |
"max_steps": 150,
|
284 |
"num_train_epochs": 1,
|
285 |
"save_steps": 5,
|
286 |
+
"total_flos": 5322104911872000.0,
|
287 |
"trial_name": null,
|
288 |
"trial_params": null
|
289 |
}
|