Training in progress, step 23000
Browse files
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5544932128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d17ba7f0bda6ad7bdf8a551f0a9de22ec3e35ffc7f7de852db391e779af37bf8
|
3 |
size 5544932128
|
last-checkpoint/adapter_config.json
CHANGED
@@ -23,13 +23,13 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": "unsloth",
|
25 |
"target_modules": [
|
26 |
-
"v_proj",
|
27 |
-
"up_proj",
|
28 |
-
"k_proj",
|
29 |
"o_proj",
|
|
|
|
|
30 |
"down_proj",
|
31 |
"gate_proj",
|
32 |
-
"
|
|
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": "unsloth",
|
25 |
"target_modules": [
|
|
|
|
|
|
|
26 |
"o_proj",
|
27 |
+
"v_proj",
|
28 |
+
"q_proj",
|
29 |
"down_proj",
|
30 |
"gate_proj",
|
31 |
+
"k_proj",
|
32 |
+
"up_proj"
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
35 |
"use_dora": false,
|
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 sha256:71cd57c0a39c9efff0f951a19c93f1b94133eba860a04cd29141f1a192bb0770
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -154,174 +154,6 @@
|
|
154 |
"learning_rate": 3.204737808427746e-05,
|
155 |
"loss": 0.5001,
|
156 |
"step": 10500
|
157 |
-
},
|
158 |
-
{
|
159 |
-
"epoch": 0.4433137704339941,
|
160 |
-
"grad_norm": 0.5442752242088318,
|
161 |
-
"learning_rate": 3.092785813443196e-05,
|
162 |
-
"loss": 0.5053,
|
163 |
-
"step": 11000
|
164 |
-
},
|
165 |
-
{
|
166 |
-
"epoch": 0.463464396362812,
|
167 |
-
"grad_norm": 0.5094788074493408,
|
168 |
-
"learning_rate": 2.9808338184586448e-05,
|
169 |
-
"loss": 0.502,
|
170 |
-
"step": 11500
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 0.48361502229162995,
|
174 |
-
"grad_norm": 0.5177408456802368,
|
175 |
-
"learning_rate": 2.8688818234740942e-05,
|
176 |
-
"loss": 0.4972,
|
177 |
-
"step": 12000
|
178 |
-
},
|
179 |
-
{
|
180 |
-
"epoch": 0.5037656482204479,
|
181 |
-
"grad_norm": 0.5165345072746277,
|
182 |
-
"learning_rate": 2.756929828489544e-05,
|
183 |
-
"loss": 0.495,
|
184 |
-
"step": 12500
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"epoch": 0.5239162741492658,
|
188 |
-
"grad_norm": 0.6729832291603088,
|
189 |
-
"learning_rate": 2.644977833504993e-05,
|
190 |
-
"loss": 0.4942,
|
191 |
-
"step": 13000
|
192 |
-
},
|
193 |
-
{
|
194 |
-
"epoch": 0.5440669000780837,
|
195 |
-
"grad_norm": 0.5211122035980225,
|
196 |
-
"learning_rate": 2.5330258385204423e-05,
|
197 |
-
"loss": 0.4928,
|
198 |
-
"step": 13500
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"epoch": 0.5642175260069016,
|
202 |
-
"grad_norm": 0.6845284104347229,
|
203 |
-
"learning_rate": 2.421073843535892e-05,
|
204 |
-
"loss": 0.4935,
|
205 |
-
"step": 14000
|
206 |
-
},
|
207 |
-
{
|
208 |
-
"epoch": 0.5843681519357194,
|
209 |
-
"grad_norm": 0.8934305906295776,
|
210 |
-
"learning_rate": 2.3091218485513413e-05,
|
211 |
-
"loss": 0.4889,
|
212 |
-
"step": 14500
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 0.6045187778645374,
|
216 |
-
"grad_norm": 0.5098538994789124,
|
217 |
-
"learning_rate": 2.1971698535667904e-05,
|
218 |
-
"loss": 0.4863,
|
219 |
-
"step": 15000
|
220 |
-
},
|
221 |
-
{
|
222 |
-
"epoch": 0.6246694037933553,
|
223 |
-
"grad_norm": 0.7277902364730835,
|
224 |
-
"learning_rate": 2.0852178585822403e-05,
|
225 |
-
"loss": 0.4866,
|
226 |
-
"step": 15500
|
227 |
-
},
|
228 |
-
{
|
229 |
-
"epoch": 0.6448200297221732,
|
230 |
-
"grad_norm": 0.5824995040893555,
|
231 |
-
"learning_rate": 1.9732658635976894e-05,
|
232 |
-
"loss": 0.4872,
|
233 |
-
"step": 16000
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 0.6649706556509911,
|
237 |
-
"grad_norm": 0.5100158452987671,
|
238 |
-
"learning_rate": 1.861313868613139e-05,
|
239 |
-
"loss": 0.4891,
|
240 |
-
"step": 16500
|
241 |
-
},
|
242 |
-
{
|
243 |
-
"epoch": 0.6851212815798091,
|
244 |
-
"grad_norm": 0.7346712946891785,
|
245 |
-
"learning_rate": 1.7493618736285884e-05,
|
246 |
-
"loss": 0.4819,
|
247 |
-
"step": 17000
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"epoch": 0.705271907508627,
|
251 |
-
"grad_norm": 0.805208146572113,
|
252 |
-
"learning_rate": 1.6374098786440375e-05,
|
253 |
-
"loss": 0.4805,
|
254 |
-
"step": 17500
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 0.7254225334374449,
|
258 |
-
"grad_norm": 0.6093766093254089,
|
259 |
-
"learning_rate": 1.5254578836594868e-05,
|
260 |
-
"loss": 0.4816,
|
261 |
-
"step": 18000
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"epoch": 0.7455731593662628,
|
265 |
-
"grad_norm": 0.5469486117362976,
|
266 |
-
"learning_rate": 1.4135058886749365e-05,
|
267 |
-
"loss": 0.4815,
|
268 |
-
"step": 18500
|
269 |
-
},
|
270 |
-
{
|
271 |
-
"epoch": 0.7657237852950808,
|
272 |
-
"grad_norm": 0.6185249090194702,
|
273 |
-
"learning_rate": 1.3015538936903856e-05,
|
274 |
-
"loss": 0.4823,
|
275 |
-
"step": 19000
|
276 |
-
},
|
277 |
-
{
|
278 |
-
"epoch": 0.7858744112238987,
|
279 |
-
"grad_norm": 0.6320446133613586,
|
280 |
-
"learning_rate": 1.189601898705835e-05,
|
281 |
-
"loss": 0.48,
|
282 |
-
"step": 19500
|
283 |
-
},
|
284 |
-
{
|
285 |
-
"epoch": 0.8060250371527166,
|
286 |
-
"grad_norm": 0.7233290672302246,
|
287 |
-
"learning_rate": 1.0776499037212844e-05,
|
288 |
-
"loss": 0.4776,
|
289 |
-
"step": 20000
|
290 |
-
},
|
291 |
-
{
|
292 |
-
"epoch": 0.8261756630815345,
|
293 |
-
"grad_norm": 0.5041834115982056,
|
294 |
-
"learning_rate": 9.656979087367337e-06,
|
295 |
-
"loss": 0.4758,
|
296 |
-
"step": 20500
|
297 |
-
},
|
298 |
-
{
|
299 |
-
"epoch": 0.8463262890103523,
|
300 |
-
"grad_norm": 0.5525909066200256,
|
301 |
-
"learning_rate": 8.53745913752183e-06,
|
302 |
-
"loss": 0.4748,
|
303 |
-
"step": 21000
|
304 |
-
},
|
305 |
-
{
|
306 |
-
"epoch": 0.8664769149391703,
|
307 |
-
"grad_norm": 0.493874192237854,
|
308 |
-
"learning_rate": 7.417939187676325e-06,
|
309 |
-
"loss": 0.4789,
|
310 |
-
"step": 21500
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"epoch": 0.8866275408679882,
|
314 |
-
"grad_norm": 0.4965188205242157,
|
315 |
-
"learning_rate": 6.298419237830819e-06,
|
316 |
-
"loss": 0.4736,
|
317 |
-
"step": 22000
|
318 |
-
},
|
319 |
-
{
|
320 |
-
"epoch": 0.9067781667968061,
|
321 |
-
"grad_norm": 0.5210591554641724,
|
322 |
-
"learning_rate": 5.178899287985312e-06,
|
323 |
-
"loss": 0.4782,
|
324 |
-
"step": 22500
|
325 |
}
|
326 |
],
|
327 |
"logging_steps": 500,
|
@@ -341,7 +173,7 @@
|
|
341 |
"attributes": {}
|
342 |
}
|
343 |
},
|
344 |
-
"total_flos":
|
345 |
"train_batch_size": 2,
|
346 |
"trial_name": null,
|
347 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.42316314450517617,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 10500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
154 |
"learning_rate": 3.204737808427746e-05,
|
155 |
"loss": 0.5001,
|
156 |
"step": 10500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
}
|
158 |
],
|
159 |
"logging_steps": 500,
|
|
|
173 |
"attributes": {}
|
174 |
}
|
175 |
},
|
176 |
+
"total_flos": 1.677250108543338e+19,
|
177 |
"train_batch_size": 2,
|
178 |
"trial_name": null,
|
179 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bfe1550ddce5e600f8af695537ba4b034ec5ea1be78e55ddc34720ae0669092
|
3 |
+
size 5176
|