Hugging Face's logo

adammandic87
/
6af1ed4c-21cc-45df-8e37-236b857c9285

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
adammandic87 commited on
Commit
73ac457
·
verified ·
1 Parent(s): 91c9726

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 sha256:2b58d3eb1217eed19f2e4e6102060b04b13f02dac1dfd9c93bdab8fac3eef1a5
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:786d0db22e2f9c4216fec157eba2a4c9eba27fa14025cc278887f78b6bd1fefa
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4322d34611a6658e45fb8dde4b68db66aacf8f907484f721dd2f6875a4299c54
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1ea9c46b799b7fb9a718678e7d7fbe542725f82c64b237fe0bc98210f681be
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
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": 0.0018042399639152007,
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": 179.795,
214
  "eval_steps_per_second": 89.897,
215
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
216
  }
217
  ],
218
  "logging_steps": 1,
@@ -232,7 +331,7 @@
232
  "attributes": {}
233
  }
234
  },
235
- "total_flos": 5848989696.0,
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": 0.0027063599458728013,
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": 179.795,
214
  "eval_steps_per_second": 89.897,
215
  "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.00187363380868117,
219
+ "grad_norm": 0.006178026087582111,
220
+ "learning_rate": 3.083613409639764e-05,
221
+ "loss": 11.933,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.0019430276534471392,
226
+ "grad_norm": 0.008088146336376667,
227
+ "learning_rate": 2.8910861626005776e-05,
228
+ "loss": 11.9318,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.0020124214982131087,
233
+ "grad_norm": 0.011524875648319721,
234
+ "learning_rate": 2.6961477393196126e-05,
235
+ "loss": 11.9309,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.0020818153429790777,
240
+ "grad_norm": 0.006601495202630758,
241
+ "learning_rate": 2.5e-05,
242
+ "loss": 11.929,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.0021512091877450472,
247
+ "grad_norm": 0.008433165028691292,
248
+ "learning_rate": 2.303852260680388e-05,
249
+ "loss": 11.9298,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.0022206030325110163,
254
+ "grad_norm": 0.010645423084497452,
255
+ "learning_rate": 2.1089138373994223e-05,
256
+ "loss": 11.9356,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.0022899968772769857,
261
+ "grad_norm": 0.0067201219499111176,
262
+ "learning_rate": 1.9163865903602374e-05,
263
+ "loss": 11.9281,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.0023593907220429548,
268
+ "grad_norm": 0.007682221010327339,
269
+ "learning_rate": 1.7274575140626318e-05,
270
+ "loss": 11.9314,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.0024287845668089243,
275
+ "grad_norm": 0.005486843641847372,
276
+ "learning_rate": 1.5432914190872757e-05,
277
+ "loss": 11.9335,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.0024981784115748933,
282
+ "grad_norm": 0.007024701684713364,
283
+ "learning_rate": 1.3650237506511331e-05,
284
+ "loss": 11.9306,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.0025675722563408628,
289
+ "grad_norm": 0.00772002711892128,
290
+ "learning_rate": 1.1937535882101281e-05,
291
+ "loss": 11.9327,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.002636966101106832,
296
+ "grad_norm": 0.005776335019618273,
297
+ "learning_rate": 1.0305368692688174e-05,
298
+ "loss": 11.9301,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.0027063599458728013,
303
+ "grad_norm": 0.005994484294205904,
304
+ "learning_rate": 8.763798791745411e-06,
305
+ "loss": 11.9322,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.0027063599458728013,
310
+ "eval_loss": 11.931797981262207,
311
+ "eval_runtime": 33.4633,
312
+ "eval_samples_per_second": 181.333,
313
+ "eval_steps_per_second": 90.667,
314
+ "step": 39
315
  }
316
  ],
317
  "logging_steps": 1,
 
331
  "attributes": {}
332
  }
333
  },
334
+ "total_flos": 8803024896.0,
335
  "train_batch_size": 2,
336
  "trial_name": null,
337
  "trial_params": null