Hugging Face's logo

dimasik87
/
63bd93dc-ce75-4513-ac10-cade1bba594e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
dimasik87 commited on
Commit
fbbfd3b
•
1 Parent(s): d29bfd1

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 +186 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70dbb07aa5cbdb247927cb5c68875d394660b2ce218a6f292eb4f2704d4fb12c
3
  size 90207248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb37c7f1390fda4f25085cb4d2bdd978d0822a3651e127ead75cc2efae5c52f
3
  size 90207248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d411a2413fc86c0a172c32582285d91423ead0284d63bb1287936045ff90a82b
3
  size 180543866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad17691905a0a147fcdaffd2f03ac91b04280e4cef606a4311393b76f6b18fc9
3
  size 180543866
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db9d1a46fd3cd18248b05a80050e831412b9a9e41ec323f47819e9f49e98a2d6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98283eb7aa86ea8a9a39a588a7edf0a1aac84a6c5eeea894980663b69e80fc0e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11b742b9f79db8ae07fe04f9aa52e116e2af2e56f41109393489fc6dbbde0882
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aec03bf87f279f0836b9767993a70ad750b638d565662d40d6a3ff55df0f361f
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": 1.0638297872340425,
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": 29.666,
199
  "eval_steps_per_second": 14.833,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -217,7 +400,7 @@
217
  "attributes": {}
218
  }
219
  },
220
- "total_flos": 4894017925939200.0,
221
  "train_batch_size": 2,
222
  "trial_name": null,
223
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.127659574468085,
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": 29.666,
199
  "eval_steps_per_second": 14.833,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.1063829787234043,
204
+ "grad_norm": 3.5807905197143555,
205
+ "learning_rate": 7.433022392834282e-05,
206
+ "loss": 2.552,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 1.148936170212766,
211
+ "grad_norm": 3.804152250289917,
212
+ "learning_rate": 7.228691778882693e-05,
213
+ "loss": 2.7359,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 1.1914893617021276,
218
+ "grad_norm": 3.969632625579834,
219
+ "learning_rate": 7.019605024359474e-05,
220
+ "loss": 2.6821,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 1.2340425531914894,
225
+ "grad_norm": 3.872260808944702,
226
+ "learning_rate": 6.806208330935766e-05,
227
+ "loss": 2.7963,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 1.2765957446808511,
232
+ "grad_norm": 2.6370015144348145,
233
+ "learning_rate": 6.588957097909508e-05,
234
+ "loss": 2.4097,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 1.3191489361702127,
239
+ "grad_norm": 3.32016658782959,
240
+ "learning_rate": 6.368314950360415e-05,
241
+ "loss": 2.4904,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 1.3617021276595744,
246
+ "grad_norm": 4.197410583496094,
247
+ "learning_rate": 6.14475274975067e-05,
248
+ "loss": 2.5286,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 1.4042553191489362,
253
+ "grad_norm": 5.017968654632568,
254
+ "learning_rate": 5.918747589082853e-05,
255
+ "loss": 2.9064,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 1.4468085106382977,
260
+ "grad_norm": 3.416367292404175,
261
+ "learning_rate": 5.6907817747594116e-05,
262
+ "loss": 2.7989,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 1.4893617021276595,
267
+ "grad_norm": 2.9843363761901855,
268
+ "learning_rate": 5.4613417973165106e-05,
269
+ "loss": 2.2761,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 1.5319148936170213,
274
+ "grad_norm": 3.322655200958252,
275
+ "learning_rate": 5.230917293228699e-05,
276
+ "loss": 2.5173,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 1.574468085106383,
281
+ "grad_norm": 4.156716823577881,
282
+ "learning_rate": 5e-05,
283
+ "loss": 2.6914,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 1.6170212765957448,
288
+ "grad_norm": 5.216977596282959,
289
+ "learning_rate": 4.7690827067713035e-05,
290
+ "loss": 3.1488,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 1.6595744680851063,
295
+ "grad_norm": 3.87528133392334,
296
+ "learning_rate": 4.5386582026834906e-05,
297
+ "loss": 2.8607,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 1.702127659574468,
302
+ "grad_norm": 2.6391236782073975,
303
+ "learning_rate": 4.30921822524059e-05,
304
+ "loss": 2.315,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 1.7446808510638299,
309
+ "grad_norm": 3.2835886478424072,
310
+ "learning_rate": 4.0812524109171476e-05,
311
+ "loss": 2.296,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 1.7872340425531914,
316
+ "grad_norm": 4.525584697723389,
317
+ "learning_rate": 3.855247250249331e-05,
318
+ "loss": 2.9909,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 1.8297872340425532,
323
+ "grad_norm": 5.08241605758667,
324
+ "learning_rate": 3.631685049639586e-05,
325
+ "loss": 2.5649,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 1.872340425531915,
330
+ "grad_norm": 3.8431763648986816,
331
+ "learning_rate": 3.411042902090492e-05,
332
+ "loss": 2.9495,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 1.9148936170212765,
337
+ "grad_norm": 2.8185856342315674,
338
+ "learning_rate": 3.1937916690642356e-05,
339
+ "loss": 2.326,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 1.9574468085106385,
344
+ "grad_norm": 3.852102518081665,
345
+ "learning_rate": 2.980394975640526e-05,
346
+ "loss": 2.4781,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 2.0,
351
+ "grad_norm": 9.235259056091309,
352
+ "learning_rate": 2.771308221117309e-05,
353
+ "loss": 4.1493,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 2.0425531914893615,
358
+ "grad_norm": 2.182204484939575,
359
+ "learning_rate": 2.5669776071657192e-05,
360
+ "loss": 2.431,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 2.0851063829787235,
365
+ "grad_norm": 2.5565974712371826,
366
+ "learning_rate": 2.3678391856132204e-05,
367
+ "loss": 2.2611,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 2.127659574468085,
372
+ "grad_norm": 3.7425453662872314,
373
+ "learning_rate": 2.1743179278870407e-05,
374
+ "loss": 2.5037,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 2.127659574468085,
379
+ "eval_loss": 2.8088538646698,
380
+ "eval_runtime": 0.6893,
381
+ "eval_samples_per_second": 29.014,
382
+ "eval_steps_per_second": 14.507,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
400
  "attributes": {}
401
  }
402
  },
403
+ "total_flos": 9788035851878400.0,
404
  "train_batch_size": 2,
405
  "trial_name": null,
406
  "trial_params": null