Hugging Face's logo

gulaschnascher4000
/
lora_0-3_3B

PEFT
TensorBoard
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Metrics Community
gulaschnascher4000 commited on
Commit
1a5aca6
·
verified ·
1 Parent(s): 2e9aa30

End of training

Browse files
Files changed (8) hide show
  1. README.md +3 -2
  2. all_results.json +12 -0
  3. eval_results.json +7 -0
  4. runs/Jan14_01-54-26_pss5xry2f0aq/events.out.tfevents.1736820201.pss5xry2f0aq.53352.1 +3 -0
  5. train_results.json +8 -0
  6. trainer_state.json +435 -0
  7. training_eval_loss.png +0 -0
  8. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.2
4
  base_model: meta-llama/Llama-3.2-3B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: lora_0-3_3B
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # lora_0-3_3B
17
 
18
- This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.7574
21
 
22
  ## Model description
23
 
 
4
  base_model: meta-llama/Llama-3.2-3B
5
  tags:
6
  - llama-factory
7
+ - lora
8
  - generated_from_trainer
9
  model-index:
10
  - name: lora_0-3_3B
 
16
 
17
  # lora_0-3_3B
18
 
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the gulaschnascher4000/stream-dataset-0-2 and the identity-chatgulaschpt datasets.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.7561
22
 
23
  ## Model description
24
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.5,
3
+ "eval_loss": 1.7560893297195435,
4
+ "eval_runtime": 51.1253,
5
+ "eval_samples_per_second": 77.163,
6
+ "eval_steps_per_second": 19.306,
7
+ "total_flos": 1.1620205475764634e+17,
8
+ "train_loss": 1.8654380205515269,
9
+ "train_runtime": 468.8189,
10
+ "train_samples_per_second": 37.866,
11
+ "train_steps_per_second": 1.184
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.5,
3
+ "eval_loss": 1.7560893297195435,
4
+ "eval_runtime": 51.1253,
5
+ "eval_samples_per_second": 77.163,
6
+ "eval_steps_per_second": 19.306
7
+ }
runs/Jan14_01-54-26_pss5xry2f0aq/events.out.tfevents.1736820201.pss5xry2f0aq.53352.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb1bbd9cb4440398edd75e19bb8fe121575b252d6bd98394b84e233f856f774
3
+ size 359
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.5,
3
+ "total_flos": 1.1620205475764634e+17,
4
+ "train_loss": 1.8654380205515269,
5
+ "train_runtime": 468.8189,
6
+ "train_samples_per_second": 37.866,
7
+ "train_steps_per_second": 1.184
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,435 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5,
5
+ "eval_steps": 500,
6
+ "global_step": 555,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009009009009009009,
13
+ "grad_norm": 1.4058982133865356,
14
+ "learning_rate": 1.785714285714286e-05,
15
+ "loss": 3.0329,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.018018018018018018,
20
+ "grad_norm": 1.5084704160690308,
21
+ "learning_rate": 3.571428571428572e-05,
22
+ "loss": 2.963,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.02702702702702703,
27
+ "grad_norm": 1.8131718635559082,
28
+ "learning_rate": 5.3571428571428575e-05,
29
+ "loss": 2.5483,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.036036036036036036,
34
+ "grad_norm": 1.7166498899459839,
35
+ "learning_rate": 7.142857142857143e-05,
36
+ "loss": 2.2173,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.04504504504504504,
41
+ "grad_norm": 1.9339869022369385,
42
+ "learning_rate": 8.92857142857143e-05,
43
+ "loss": 2.0999,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.05405405405405406,
48
+ "grad_norm": 1.7656594514846802,
49
+ "learning_rate": 9.998414611537681e-05,
50
+ "loss": 2.065,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.06306306306306306,
55
+ "grad_norm": 1.831594467163086,
56
+ "learning_rate": 9.980590535514233e-05,
57
+ "loss": 2.0001,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.07207207207207207,
62
+ "grad_norm": 1.879267692565918,
63
+ "learning_rate": 9.943031509146825e-05,
64
+ "loss": 1.9977,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.08108108108108109,
69
+ "grad_norm": 1.8009542226791382,
70
+ "learning_rate": 9.885886355253758e-05,
71
+ "loss": 2.0185,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.09009009009009009,
76
+ "grad_norm": 1.7639012336730957,
77
+ "learning_rate": 9.809381504168234e-05,
78
+ "loss": 1.9265,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.0990990990990991,
83
+ "grad_norm": 1.8977757692337036,
84
+ "learning_rate": 9.713820096537225e-05,
85
+ "loss": 1.9129,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.10810810810810811,
90
+ "grad_norm": 2.3275864124298096,
91
+ "learning_rate": 9.599580782165598e-05,
92
+ "loss": 1.9642,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.11711711711711711,
97
+ "grad_norm": 1.7085381746292114,
98
+ "learning_rate": 9.467116219664894e-05,
99
+ "loss": 1.9043,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.12612612612612611,
104
+ "grad_norm": 1.9735201597213745,
105
+ "learning_rate": 9.316951282851707e-05,
106
+ "loss": 1.8833,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.13513513513513514,
111
+ "grad_norm": 1.8018202781677246,
112
+ "learning_rate": 9.149680981002609e-05,
113
+ "loss": 1.9395,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.14414414414414414,
118
+ "grad_norm": 2.0004780292510986,
119
+ "learning_rate": 8.965968101206291e-05,
120
+ "loss": 1.8237,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.15315315315315314,
125
+ "grad_norm": 1.8323822021484375,
126
+ "learning_rate": 8.766540582154859e-05,
127
+ "loss": 1.9039,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.16216216216216217,
132
+ "grad_norm": 2.0277061462402344,
133
+ "learning_rate": 8.552188629780244e-05,
134
+ "loss": 1.8434,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.17117117117117117,
139
+ "grad_norm": 1.9151962995529175,
140
+ "learning_rate": 8.323761586164695e-05,
141
+ "loss": 1.8668,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.18018018018018017,
146
+ "grad_norm": 1.985343098640442,
147
+ "learning_rate": 8.082164564131845e-05,
148
+ "loss": 1.8238,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.1891891891891892,
153
+ "grad_norm": 1.9954603910446167,
154
+ "learning_rate": 7.828354860853399e-05,
155
+ "loss": 1.8616,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.1981981981981982,
160
+ "grad_norm": 2.0763890743255615,
161
+ "learning_rate": 7.563338164682036e-05,
162
+ "loss": 1.795,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.2072072072072072,
167
+ "grad_norm": 2.1642045974731445,
168
+ "learning_rate": 7.288164570240463e-05,
169
+ "loss": 1.7992,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.21621621621621623,
174
+ "grad_norm": 1.9592050313949585,
175
+ "learning_rate": 7.003924417556343e-05,
176
+ "loss": 1.7634,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.22522522522522523,
181
+ "grad_norm": 2.011563777923584,
182
+ "learning_rate": 6.711743971729967e-05,
183
+ "loss": 1.796,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.23423423423423423,
188
+ "grad_norm": 2.1861069202423096,
189
+ "learning_rate": 6.412780960253436e-05,
190
+ "loss": 1.839,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.24324324324324326,
195
+ "grad_norm": 2.18581223487854,
196
+ "learning_rate": 6.108219985664161e-05,
197
+ "loss": 1.8259,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.25225225225225223,
202
+ "grad_norm": 2.018559694290161,
203
+ "learning_rate": 5.799267831709442e-05,
204
+ "loss": 1.7566,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.26126126126126126,
209
+ "grad_norm": 2.043818950653076,
210
+ "learning_rate": 5.487148681620862e-05,
211
+ "loss": 1.7795,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.2702702702702703,
216
+ "grad_norm": 2.263270854949951,
217
+ "learning_rate": 5.173099267445451e-05,
218
+ "loss": 1.7507,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.27927927927927926,
223
+ "grad_norm": 2.139925241470337,
224
+ "learning_rate": 4.858363969653781e-05,
225
+ "loss": 1.7462,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.2882882882882883,
230
+ "grad_norm": 2.1028239727020264,
231
+ "learning_rate": 4.544189886442162e-05,
232
+ "loss": 1.8059,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.2972972972972973,
237
+ "grad_norm": 2.3162405490875244,
238
+ "learning_rate": 4.23182189226621e-05,
239
+ "loss": 1.7456,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.3063063063063063,
244
+ "grad_norm": 2.153001546859741,
245
+ "learning_rate": 3.9224977051856904e-05,
246
+ "loss": 1.7294,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.3153153153153153,
251
+ "grad_norm": 2.3347864151000977,
252
+ "learning_rate": 3.6174429825656685e-05,
253
+ "loss": 1.7287,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.32432432432432434,
258
+ "grad_norm": 2.408170700073242,
259
+ "learning_rate": 3.3178664645666066e-05,
260
+ "loss": 1.7555,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.3333333333333333,
265
+ "grad_norm": 2.102254629135132,
266
+ "learning_rate": 3.0249551846667207e-05,
267
+ "loss": 1.7149,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.34234234234234234,
272
+ "grad_norm": 2.818976640701294,
273
+ "learning_rate": 2.739869766194263e-05,
274
+ "loss": 1.7532,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.35135135135135137,
279
+ "grad_norm": 2.4131245613098145,
280
+ "learning_rate": 2.4637398235066527e-05,
281
+ "loss": 1.6948,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.36036036036036034,
286
+ "grad_norm": 2.3351337909698486,
287
+ "learning_rate": 2.1976594860386597e-05,
288
+ "loss": 1.7533,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.36936936936936937,
293
+ "grad_norm": 2.7150731086730957,
294
+ "learning_rate": 1.9426830629550242e-05,
295
+ "loss": 1.7752,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.3783783783783784,
300
+ "grad_norm": 2.3618431091308594,
301
+ "learning_rate": 1.6998208655858137e-05,
302
+ "loss": 1.7286,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.38738738738738737,
307
+ "grad_norm": 2.6013503074645996,
308
+ "learning_rate": 1.4700352041975168e-05,
309
+ "loss": 1.7331,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.3963963963963964,
314
+ "grad_norm": 2.411003351211548,
315
+ "learning_rate": 1.2542365749622049e-05,
316
+ "loss": 1.7582,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.40540540540540543,
321
+ "grad_norm": 2.211366891860962,
322
+ "learning_rate": 1.0532800522333902e-05,
323
+ "loss": 1.6628,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.4144144144144144,
328
+ "grad_norm": 2.5683863162994385,
329
+ "learning_rate": 8.67961900423711e-06,
330
+ "loss": 1.6957,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.42342342342342343,
335
+ "grad_norm": 2.2518529891967773,
336
+ "learning_rate": 6.990164189094589e-06,
337
+ "loss": 1.7118,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.43243243243243246,
342
+ "grad_norm": 2.4307000637054443,
343
+ "learning_rate": 5.4711303246361144e-06,
344
+ "loss": 1.6488,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.44144144144144143,
349
+ "grad_norm": 2.3331761360168457,
350
+ "learning_rate": 4.12853638746134e-06,
351
+ "loss": 1.6793,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.45045045045045046,
356
+ "grad_norm": 2.3686130046844482,
357
+ "learning_rate": 2.9677022336181413e-06,
358
+ "loss": 1.6649,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.45045045045045046,
363
+ "eval_loss": 1.7574011087417603,
364
+ "eval_runtime": 51.3954,
365
+ "eval_samples_per_second": 76.758,
366
+ "eval_steps_per_second": 19.204,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 0.4594594594594595,
371
+ "grad_norm": 2.348306655883789,
372
+ "learning_rate": 1.993227519356189e-06,
373
+ "loss": 1.7905,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 0.46846846846846846,
378
+ "grad_norm": 2.5951645374298096,
379
+ "learning_rate": 1.208973475579761e-06,
380
+ "loss": 1.7358,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 0.4774774774774775,
385
+ "grad_norm": 2.408781051635742,
386
+ "learning_rate": 6.180476082162656e-07,
387
+ "loss": 1.7079,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 0.4864864864864865,
392
+ "grad_norm": 2.519191265106201,
393
+ "learning_rate": 2.2279138512300567e-07,
394
+ "loss": 1.6984,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 0.4954954954954955,
399
+ "grad_norm": 2.511556625366211,
400
+ "learning_rate": 2.4770958321568283e-08,
401
+ "loss": 1.637,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 0.5,
406
+ "step": 555,
407
+ "total_flos": 1.1620205475764634e+17,
408
+ "train_loss": 1.8654380205515269,
409
+ "train_runtime": 468.8189,
410
+ "train_samples_per_second": 37.866,
411
+ "train_steps_per_second": 1.184
412
+ }
413
+ ],
414
+ "logging_steps": 10,
415
+ "max_steps": 555,
416
+ "num_input_tokens_seen": 0,
417
+ "num_train_epochs": 1,
418
+ "save_steps": 50000,
419
+ "stateful_callbacks": {
420
+ "TrainerControl": {
421
+ "args": {
422
+ "should_epoch_stop": false,
423
+ "should_evaluate": false,
424
+ "should_log": false,
425
+ "should_save": true,
426
+ "should_training_stop": true
427
+ },
428
+ "attributes": {}
429
+ }
430
+ },
431
+ "total_flos": 1.1620205475764634e+17,
432
+ "train_batch_size": 8,
433
+ "trial_name": null,
434
+ "trial_params": null
435
+ }
training_eval_loss.png ADDED
training_loss.png ADDED