Training in progress, step 43, 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 +130 -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 70430032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:822bc2ffc730d54c877acb1f40f8698afc4976d1824333455c8d315f85280e4e
|
3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 141053442
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612b269f60aca2c96227b2d18b3be85eb8b027ab3ec20db0f6fb0e8a4f8c1295
|
3 |
size 141053442
|
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 14960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2da2ff6f33c98d8795d59988d31e2854b66c40ed5f9eb5ae518eb81c6c4dab51
|
3 |
size 14960
|
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 sha256:62301e80c7598b8950632611ebfa03646637d97848f872bf7d1a304382a034d4
|
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:f0a0b7eac5d5eeb6a82e665caa24d67eaf6d4ac0cd22b33a51fa0a9847ed1fb3
|
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 sha256:416c1afc422120318bfb15e151d140e32cb7366313329428b2e93cdac85c2615
|
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:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
|
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":
|
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 +198,132 @@
|
|
198 |
"eval_samples_per_second": 33.509,
|
199 |
"eval_steps_per_second": 8.712,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -212,12 +338,12 @@
|
|
212 |
"should_evaluate": false,
|
213 |
"should_log": false,
|
214 |
"should_save": true,
|
215 |
-
"should_training_stop":
|
216 |
},
|
217 |
"attributes": {}
|
218 |
}
|
219 |
},
|
220 |
-
"total_flos":
|
221 |
"train_batch_size": 1,
|
222 |
"trial_name": null,
|
223 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0645879732739423,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 43,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 33.509,
|
199 |
"eval_steps_per_second": 8.712,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.8530066815144766,
|
204 |
+
"grad_norm": 0.8329769372940063,
|
205 |
+
"learning_rate": 4.307583240115024e-05,
|
206 |
+
"loss": 0.1588,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.9242761692650334,
|
211 |
+
"grad_norm": 1.176580548286438,
|
212 |
+
"learning_rate": 3.9789240471617385e-05,
|
213 |
+
"loss": 0.1374,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.9955456570155903,
|
218 |
+
"grad_norm": 0.6185368895530701,
|
219 |
+
"learning_rate": 3.659191132728971e-05,
|
220 |
+
"loss": 0.2032,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.066815144766147,
|
225 |
+
"grad_norm": 3.2315216064453125,
|
226 |
+
"learning_rate": 3.350260816694816e-05,
|
227 |
+
"loss": 0.514,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.138084632516704,
|
232 |
+
"grad_norm": 0.7700513601303101,
|
233 |
+
"learning_rate": 3.0539460249945056e-05,
|
234 |
+
"loss": 0.1931,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.2093541202672604,
|
239 |
+
"grad_norm": 0.5963460206985474,
|
240 |
+
"learning_rate": 2.7719856506501306e-05,
|
241 |
+
"loss": 0.1288,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.2806236080178173,
|
246 |
+
"grad_norm": 0.5300996899604797,
|
247 |
+
"learning_rate": 2.5060343492549566e-05,
|
248 |
+
"loss": 0.1928,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.351893095768374,
|
253 |
+
"grad_norm": 0.9159259796142578,
|
254 |
+
"learning_rate": 2.257652828796459e-05,
|
255 |
+
"loss": 0.1928,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 2.423162583518931,
|
260 |
+
"grad_norm": 0.8254880905151367,
|
261 |
+
"learning_rate": 2.0282986908012567e-05,
|
262 |
+
"loss": 0.1319,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 2.494432071269488,
|
267 |
+
"grad_norm": 0.6946773529052734,
|
268 |
+
"learning_rate": 1.819317876549771e-05,
|
269 |
+
"loss": 0.2188,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 2.5657015590200447,
|
274 |
+
"grad_norm": 0.7235588431358337,
|
275 |
+
"learning_rate": 1.631936768557596e-05,
|
276 |
+
"loss": 0.2069,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 2.6369710467706016,
|
281 |
+
"grad_norm": 0.5640904903411865,
|
282 |
+
"learning_rate": 1.4672549936752506e-05,
|
283 |
+
"loss": 0.1033,
|
284 |
+
"step": 37
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.708240534521158,
|
288 |
+
"grad_norm": 0.5563797354698181,
|
289 |
+
"learning_rate": 1.3262389700405744e-05,
|
290 |
+
"loss": 0.1157,
|
291 |
+
"step": 38
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 2.779510022271715,
|
295 |
+
"grad_norm": 0.6494319438934326,
|
296 |
+
"learning_rate": 1.2097162357528127e-05,
|
297 |
+
"loss": 0.2194,
|
298 |
+
"step": 39
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 2.8507795100222717,
|
302 |
+
"grad_norm": 0.6779353022575378,
|
303 |
+
"learning_rate": 1.1183705925499948e-05,
|
304 |
+
"loss": 0.1103,
|
305 |
+
"step": 40
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 2.9220489977728286,
|
309 |
+
"grad_norm": 0.7211727499961853,
|
310 |
+
"learning_rate": 1.0527380929884324e-05,
|
311 |
+
"loss": 0.1513,
|
312 |
+
"step": 41
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 2.9933184855233854,
|
316 |
+
"grad_norm": 0.5112365484237671,
|
317 |
+
"learning_rate": 1.013203894673168e-05,
|
318 |
+
"loss": 0.1698,
|
319 |
+
"step": 42
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 3.0645879732739423,
|
323 |
+
"grad_norm": 5.871841907501221,
|
324 |
+
"learning_rate": 1e-05,
|
325 |
+
"loss": 0.5043,
|
326 |
+
"step": 43
|
327 |
}
|
328 |
],
|
329 |
"logging_steps": 1,
|
|
|
338 |
"should_evaluate": false,
|
339 |
"should_log": false,
|
340 |
"should_save": true,
|
341 |
+
"should_training_stop": true
|
342 |
},
|
343 |
"attributes": {}
|
344 |
}
|
345 |
},
|
346 |
+
"total_flos": 4.049313816222106e+16,
|
347 |
"train_batch_size": 1,
|
348 |
"trial_name": null,
|
349 |
"trial_params": null
|