Hugging Face's logo

0x1202
/
67a992f4-04ea-4b25-84a9-4fc258302d90

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
0x1202 commited on
Commit
884fd4c
·
verified ·
1 Parent(s): 1a06685

Training in progress, step 50, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +189 -6
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ea915ed350288b9e53847205d854744c45ba764d0ee49803cee94d7224ac91f
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d17878c8eea4c53e4eae77f7fe83d8a3c7304f765ca05fcd54874393d9ba4ad7
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b7da45bb413218290387766443db8f13c9b2ec48ecbbd99605abe178dbc30c
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7dfa2bc2620b339f066aa10d66c5e94d2c4236399fbd2f5618abd18513bb9f1
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:394d79bd9ac663f1c19723ed1141821ced6d884b8927b99c91f1b2d204771ecd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6d17f5d3e6977f4a967ef3207a5dc14265e37caf420f5cf5b8d578a4d7e7ca
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.3726862370967865,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.01886080724254998,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -198,6 +198,189 @@
198
  "eval_samples_per_second": 109.666,
199
  "eval_steps_per_second": 13.751,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +404,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 1033684525252608.0,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3445923328399658,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.03772161448509996,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 109.666,
199
  "eval_steps_per_second": 13.751,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.01961523953225198,
204
+ "grad_norm": 0.7956138849258423,
205
+ "learning_rate": 5.522642316338268e-05,
206
+ "loss": 0.3527,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.02036967182195398,
211
+ "grad_norm": 0.8124170899391174,
212
+ "learning_rate": 5.174497483512506e-05,
213
+ "loss": 0.2873,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.021124104111655977,
218
+ "grad_norm": 0.878582239151001,
219
+ "learning_rate": 4.825502516487497e-05,
220
+ "loss": 0.3622,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.02187853640135798,
225
+ "grad_norm": 0.9804088473320007,
226
+ "learning_rate": 4.477357683661734e-05,
227
+ "loss": 0.3978,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.022632968691059976,
232
+ "grad_norm": 0.8588770031929016,
233
+ "learning_rate": 4.131759111665349e-05,
234
+ "loss": 0.2956,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.023387400980761978,
239
+ "grad_norm": 0.783898115158081,
240
+ "learning_rate": 3.790390522001662e-05,
241
+ "loss": 0.301,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.024141833270463976,
246
+ "grad_norm": 0.6420652270317078,
247
+ "learning_rate": 3.4549150281252636e-05,
248
+ "loss": 0.2105,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.024896265560165973,
253
+ "grad_norm": 1.0156136751174927,
254
+ "learning_rate": 3.12696703292044e-05,
255
+ "loss": 0.3051,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.025650697849867975,
260
+ "grad_norm": 0.7897914052009583,
261
+ "learning_rate": 2.8081442660546125e-05,
262
+ "loss": 0.3269,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.026405130139569973,
267
+ "grad_norm": 0.7197304368019104,
268
+ "learning_rate": 2.500000000000001e-05,
269
+ "loss": 0.2039,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.027159562429271974,
274
+ "grad_norm": 0.8324704170227051,
275
+ "learning_rate": 2.2040354826462668e-05,
276
+ "loss": 0.3202,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.02791399471897397,
281
+ "grad_norm": 0.8574749231338501,
282
+ "learning_rate": 1.9216926233717085e-05,
283
+ "loss": 0.2887,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.028668427008675973,
288
+ "grad_norm": 1.0728785991668701,
289
+ "learning_rate": 1.6543469682057106e-05,
290
+ "loss": 0.4163,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.02942285929837797,
295
+ "grad_norm": 0.9155979156494141,
296
+ "learning_rate": 1.4033009983067452e-05,
297
+ "loss": 0.2978,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.03017729158807997,
302
+ "grad_norm": 0.8738413453102112,
303
+ "learning_rate": 1.1697777844051105e-05,
304
+ "loss": 0.3142,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.03093172387778197,
309
+ "grad_norm": 0.89309161901474,
310
+ "learning_rate": 9.549150281252633e-06,
311
+ "loss": 0.2975,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.03168615616748397,
316
+ "grad_norm": 1.0845947265625,
317
+ "learning_rate": 7.597595192178702e-06,
318
+ "loss": 0.3054,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.03244058845718597,
323
+ "grad_norm": 0.9354661107063293,
324
+ "learning_rate": 5.852620357053651e-06,
325
+ "loss": 0.3257,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.03319502074688797,
330
+ "grad_norm": 1.173690676689148,
331
+ "learning_rate": 4.322727117869951e-06,
332
+ "loss": 0.3655,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.033949453036589965,
337
+ "grad_norm": 0.984697699546814,
338
+ "learning_rate": 3.0153689607045845e-06,
339
+ "loss": 0.2914,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.03470388532629196,
344
+ "grad_norm": 1.103393316268921,
345
+ "learning_rate": 1.9369152030840556e-06,
346
+ "loss": 0.3537,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.03545831761599397,
351
+ "grad_norm": 1.3742722272872925,
352
+ "learning_rate": 1.0926199633097157e-06,
353
+ "loss": 0.4048,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.036212749905695965,
358
+ "grad_norm": 1.5404117107391357,
359
+ "learning_rate": 4.865965629214819e-07,
360
+ "loss": 0.4235,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.03696718219539796,
365
+ "grad_norm": 1.8669302463531494,
366
+ "learning_rate": 1.2179748700879012e-07,
367
+ "loss": 0.3197,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.03772161448509996,
372
+ "grad_norm": 3.114102602005005,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.5909,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03772161448509996,
379
+ "eval_loss": 0.3445923328399658,
380
+ "eval_runtime": 20.3648,
381
+ "eval_samples_per_second": 109.65,
382
+ "eval_steps_per_second": 13.749,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
+ "should_training_stop": true
408
  },
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 1999744829227008.0,
413
  "train_batch_size": 8,
414
  "trial_name": null,
415
  "trial_params": null