DeepDream2045
commited on
Commit
•
9e7dd27
1
Parent(s):
4f46fe8
Training in progress, step 36, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +81 -4
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc698f29b5bd4395eba500467e69f010931c71c5b2370377f772025a4cb34e76
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b12ed38f2554f877e3dda7e6d31003b997e5ed3b760a92a5a57dc276279d868f
|
3 |
size 640009682
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:683b0515f2e48757b1d1b12171fdbaf9562daa30f7b80ee249d6f54a8963ab4c
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7169452b3bd8c83ac883fbdddda2d02deac0b966334dc0ba8d64f38cda8a1ade
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d65ecbcc70c961762e72976b50b0d88898224c45afd62af48d0795749b92422
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90d6b9a21f2476e669a0c031ad1a0498569beab5877a919a8734a74508acb73a
|
3 |
size 15024
|
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 sha256:28651c349f447d90467a1ab072123a42ef3fcd558c7e8a7b853a87ba29324613
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.2715974450111389,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -198,6 +198,83 @@
|
|
198 |
"eval_samples_per_second": 19.037,
|
199 |
"eval_steps_per_second": 2.38,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +298,12 @@
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
-
"should_training_stop":
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
-
"total_flos":
|
230 |
"train_batch_size": 2,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.2715974450111389,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
+
"epoch": 3.031578947368421,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 36,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 19.037,
|
199 |
"eval_steps_per_second": 2.38,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.1894736842105265,
|
204 |
+
"grad_norm": 0.04599270597100258,
|
205 |
+
"learning_rate": 1.9868268181037185e-05,
|
206 |
+
"loss": 0.0012,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.2736842105263158,
|
211 |
+
"grad_norm": 2.79744291305542,
|
212 |
+
"learning_rate": 1.631521781767214e-05,
|
213 |
+
"loss": 0.1034,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 2.3578947368421055,
|
218 |
+
"grad_norm": 2.700434684753418,
|
219 |
+
"learning_rate": 1.3049554138967051e-05,
|
220 |
+
"loss": 0.4264,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.442105263157895,
|
225 |
+
"grad_norm": 0.027330536395311356,
|
226 |
+
"learning_rate": 1.0099138635988026e-05,
|
227 |
+
"loss": 0.0008,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.526315789473684,
|
232 |
+
"grad_norm": 4.523248195648193,
|
233 |
+
"learning_rate": 7.489143213519301e-06,
|
234 |
+
"loss": 0.175,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.610526315789474,
|
239 |
+
"grad_norm": 2.505566358566284,
|
240 |
+
"learning_rate": 5.241835432246889e-06,
|
241 |
+
"loss": 0.2446,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.694736842105263,
|
246 |
+
"grad_norm": 0.018715698271989822,
|
247 |
+
"learning_rate": 3.376388529782215e-06,
|
248 |
+
"loss": 0.0006,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.7789473684210524,
|
253 |
+
"grad_norm": 4.404769420623779,
|
254 |
+
"learning_rate": 1.908717841359048e-06,
|
255 |
+
"loss": 0.3044,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 2.863157894736842,
|
260 |
+
"grad_norm": 1.9680789709091187,
|
261 |
+
"learning_rate": 8.513450158049108e-07,
|
262 |
+
"loss": 0.1945,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 2.9473684210526314,
|
267 |
+
"grad_norm": 2.3198118209838867,
|
268 |
+
"learning_rate": 2.1329118524827662e-07,
|
269 |
+
"loss": 0.0721,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 3.031578947368421,
|
274 |
+
"grad_norm": 2.005392074584961,
|
275 |
+
"learning_rate": 0.0,
|
276 |
+
"loss": 0.1797,
|
277 |
+
"step": 36
|
278 |
}
|
279 |
],
|
280 |
"logging_steps": 1,
|
|
|
298 |
"should_evaluate": false,
|
299 |
"should_log": false,
|
300 |
"should_save": true,
|
301 |
+
"should_training_stop": true
|
302 |
},
|
303 |
"attributes": {}
|
304 |
}
|
305 |
},
|
306 |
+
"total_flos": 5.610862382625587e+17,
|
307 |
"train_batch_size": 2,
|
308 |
"trial_name": null,
|
309 |
"trial_params": null
|