Hugging Face's logo

daniel40
/
8d6e9e4f-e643-4ede-b786-082adcd7c58a

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
daniel40 commited on
Commit
8138aa4
·
verified ·
1 Parent(s): 9bfd18b

Training in progress, step 39, 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 +102 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65ae6ff9f1063291387e983e30f827373245bfd5af046008d4c7928ef243aa8e
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d7303fa8c1f799dea3cdc1e75e5ba76ee1fe15a8f94ca16cb18a5d6c1f60ec
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f748d091324b47fdfe9af447735b7a0c06856154c4111fb50512176c90d62baa
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04abb35671af26fd0e178f8456116c6478c3d12e5b340e5e7a50278d701f5e44
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f88e356060eb5c80f81f491adfeea780178f8be24fcb16d7e89fb4c497bfcfbc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa3a4caf35fd209d48f11310346c98ca5b35cff91643ace351650698faea638
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
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": 0.025851354710415112,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -213,6 +213,105 @@
213
  "eval_samples_per_second": 12.492,
214
  "eval_steps_per_second": 6.246,
215
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
216
  }
217
  ],
218
  "logging_steps": 1,
@@ -232,7 +331,7 @@
232
  "attributes": {}
233
  }
234
  },
235
- "total_flos": 9492320480133120.0,
236
  "train_batch_size": 2,
237
  "trial_name": null,
238
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03877703206562267,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
213
  "eval_samples_per_second": 12.492,
214
  "eval_steps_per_second": 6.246,
215
  "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.026845637583892617,
219
+ "grad_norm": 0.6172102093696594,
220
+ "learning_rate": 3.083613409639764e-05,
221
+ "loss": 1.3252,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.02783992045737012,
226
+ "grad_norm": 0.5786134600639343,
227
+ "learning_rate": 2.8910861626005776e-05,
228
+ "loss": 1.0781,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.028834203330847626,
233
+ "grad_norm": 0.6131380796432495,
234
+ "learning_rate": 2.6961477393196126e-05,
235
+ "loss": 1.4603,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.02982848620432513,
240
+ "grad_norm": 0.5507011413574219,
241
+ "learning_rate": 2.5e-05,
242
+ "loss": 0.9635,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.030822769077802636,
247
+ "grad_norm": 0.5960745215415955,
248
+ "learning_rate": 2.303852260680388e-05,
249
+ "loss": 1.1379,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.03181705195128014,
254
+ "grad_norm": 0.5253822207450867,
255
+ "learning_rate": 2.1089138373994223e-05,
256
+ "loss": 0.9897,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.03281133482475764,
261
+ "grad_norm": 0.6236615777015686,
262
+ "learning_rate": 1.9163865903602374e-05,
263
+ "loss": 1.083,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.033805617698235146,
268
+ "grad_norm": 0.5677335858345032,
269
+ "learning_rate": 1.7274575140626318e-05,
270
+ "loss": 1.2313,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.03479990057171265,
275
+ "grad_norm": 0.5143101215362549,
276
+ "learning_rate": 1.5432914190872757e-05,
277
+ "loss": 1.062,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.035794183445190156,
282
+ "grad_norm": 0.48625993728637695,
283
+ "learning_rate": 1.3650237506511331e-05,
284
+ "loss": 1.2285,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.03678846631866766,
289
+ "grad_norm": 0.5220788717269897,
290
+ "learning_rate": 1.1937535882101281e-05,
291
+ "loss": 1.0257,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.037782749192145165,
296
+ "grad_norm": 0.5212054252624512,
297
+ "learning_rate": 1.0305368692688174e-05,
298
+ "loss": 0.9489,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.03877703206562267,
303
+ "grad_norm": 0.5077629685401917,
304
+ "learning_rate": 8.763798791745411e-06,
305
+ "loss": 1.129,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.03877703206562267,
310
+ "eval_loss": 1.0944116115570068,
311
+ "eval_runtime": 33.9486,
312
+ "eval_samples_per_second": 12.489,
313
+ "eval_steps_per_second": 6.245,
314
+ "step": 39
315
  }
316
  ],
317
  "logging_steps": 1,
 
331
  "attributes": {}
332
  }
333
  },
334
+ "total_flos": 1.3904966757384192e+16,
335
  "train_batch_size": 2,
336
  "trial_name": null,
337
  "trial_params": null