File size: 23,307 Bytes
d16fbc5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
06/17/2024 20:24:18 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

06/17/2024 20:24:18 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>

06/17/2024 20:24:22 - INFO - llamafactory.data.loader - Loading dataset llamafactory/glaive_toolcall_en...

06/17/2024 20:24:27 - INFO - llamafactory.data.loader - Loading dataset llamafactory/glaive_toolcall_zh...

06/17/2024 20:24:32 - INFO - llamafactory.data.loader - Loading dataset llamafactory/glaive_toolcall_en...

06/17/2024 20:24:36 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/config.json

06/17/2024 20:24:36 - INFO - transformers.configuration_utils - Model config Qwen2Config {
  "_name_or_path": "Qwen/Qwen2-7B-Instruct",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}


06/17/2024 20:24:36 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit.

06/17/2024 20:24:36 - INFO - transformers.modeling_utils - loading weights file model.safetensors from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/model.safetensors.index.json

06/17/2024 20:24:36 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float16.

06/17/2024 20:24:36 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
  "bos_token_id": 151643,
  "eos_token_id": 151645
}


06/17/2024 20:24:37 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit.

06/17/2024 20:25:04 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing Qwen2ForCausalLM.


06/17/2024 20:25:04 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-7B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.

06/17/2024 20:25:04 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.

06/17/2024 20:25:04 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

06/17/2024 20:25:04 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.

06/17/2024 20:25:04 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA

06/17/2024 20:25:04 - INFO - llamafactory.model.model_utils.misc - Found linear modules: o_proj,k_proj,up_proj,gate_proj,v_proj,q_proj,down_proj

06/17/2024 20:25:04 - INFO - transformers.generation.configuration_utils - loading configuration file generation_config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/generation_config.json

06/17/2024 20:25:04 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
  "bos_token_id": 151643,
  "do_sample": true,
  "eos_token_id": [
    151645,
    151643
  ],
  "pad_token_id": 151643,
  "repetition_penalty": 1.05,
  "temperature": 0.7,
  "top_k": 20,
  "top_p": 0.8
}


06/17/2024 20:25:04 - INFO - llamafactory.model.loader - trainable params: 20185088 || all params: 7635801600 || trainable%: 0.2643

06/17/2024 20:25:04 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.

06/17/2024 20:25:04 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.

06/17/2024 20:25:04 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.

06/17/2024 20:25:04 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA

06/17/2024 20:25:04 - INFO - llamafactory.model.model_utils.misc - Found linear modules: o_proj,up_proj,down_proj,q_proj,v_proj,k_proj,gate_proj

06/17/2024 20:25:05 - INFO - llamafactory.model.loader - trainable params: 20185088 || all params: 7635801600 || trainable%: 0.2643

06/17/2024 20:25:05 - WARNING - accelerate.utils.other - Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.

06/17/2024 20:25:05 - INFO - transformers.trainer - Using auto half precision backend

06/17/2024 20:25:05 - INFO - transformers.trainer - ***** Running training *****

06/17/2024 20:25:05 - INFO - transformers.trainer -   Num examples = 2,000

06/17/2024 20:25:05 - INFO - transformers.trainer -   Num Epochs = 3

06/17/2024 20:25:05 - INFO - transformers.trainer -   Instantaneous batch size per device = 1

06/17/2024 20:25:05 - INFO - transformers.trainer -   Total train batch size (w. parallel, distributed & accumulation) = 16

06/17/2024 20:25:05 - INFO - transformers.trainer -   Gradient Accumulation steps = 8

06/17/2024 20:25:05 - INFO - transformers.trainer -   Total optimization steps = 375

06/17/2024 20:25:05 - INFO - transformers.trainer -   Number of trainable parameters = 20,185,088

06/17/2024 20:26:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.6880, 'learning_rate': 4.9978e-05, 'epoch': 0.04, 'throughput': 807.59}

06/17/2024 20:26:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.7630, 'learning_rate': 4.9912e-05, 'epoch': 0.08, 'throughput': 788.63}

06/17/2024 20:27:47 - INFO - llamafactory.extras.callbacks - {'loss': 0.6882, 'learning_rate': 4.9803e-05, 'epoch': 0.12, 'throughput': 782.46}

06/17/2024 20:28:41 - INFO - llamafactory.extras.callbacks - {'loss': 0.6951, 'learning_rate': 4.9650e-05, 'epoch': 0.16, 'throughput': 778.58}

06/17/2024 20:29:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.5008, 'learning_rate': 4.9454e-05, 'epoch': 0.20, 'throughput': 776.76}

06/17/2024 20:30:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.5420, 'learning_rate': 4.9215e-05, 'epoch': 0.24, 'throughput': 780.46}

06/17/2024 20:31:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.5369, 'learning_rate': 4.8933e-05, 'epoch': 0.28, 'throughput': 781.27}

06/17/2024 20:32:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.4948, 'learning_rate': 4.8609e-05, 'epoch': 0.32, 'throughput': 780.39}

06/17/2024 20:32:52 - INFO - llamafactory.extras.callbacks - {'loss': 0.5244, 'learning_rate': 4.8244e-05, 'epoch': 0.36, 'throughput': 778.70}

06/17/2024 20:33:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.4210, 'learning_rate': 4.7839e-05, 'epoch': 0.40, 'throughput': 780.25}

06/17/2024 20:34:25 - INFO - llamafactory.extras.callbacks - {'loss': 0.4517, 'learning_rate': 4.7393e-05, 'epoch': 0.44, 'throughput': 779.83}

06/17/2024 20:35:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.4661, 'learning_rate': 4.6908e-05, 'epoch': 0.48, 'throughput': 775.58}

06/17/2024 20:36:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.4928, 'learning_rate': 4.6384e-05, 'epoch': 0.52, 'throughput': 775.62}

06/17/2024 20:37:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.5424, 'learning_rate': 4.5823e-05, 'epoch': 0.56, 'throughput': 775.79}

06/17/2024 20:37:52 - INFO - llamafactory.extras.callbacks - {'loss': 0.5419, 'learning_rate': 4.5225e-05, 'epoch': 0.60, 'throughput': 774.15}

06/17/2024 20:38:39 - INFO - llamafactory.extras.callbacks - {'loss': 0.4558, 'learning_rate': 4.4592e-05, 'epoch': 0.64, 'throughput': 774.75}

06/17/2024 20:39:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.5656, 'learning_rate': 4.3925e-05, 'epoch': 0.68, 'throughput': 776.75}

06/17/2024 20:40:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.4832, 'learning_rate': 4.3224e-05, 'epoch': 0.72, 'throughput': 780.75}

06/17/2024 20:41:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.4626, 'learning_rate': 4.2492e-05, 'epoch': 0.76, 'throughput': 781.15}

06/17/2024 20:41:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.4837, 'learning_rate': 4.1728e-05, 'epoch': 0.80, 'throughput': 780.33}

06/17/2024 20:41:56 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-100

06/17/2024 20:41:57 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/config.json

06/17/2024 20:41:57 - INFO - transformers.configuration_utils - Model config Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}


06/17/2024 20:41:57 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-100/tokenizer_config.json

06/17/2024 20:41:57 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-100/special_tokens_map.json

06/17/2024 20:42:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.5144, 'learning_rate': 4.0936e-05, 'epoch': 0.84, 'throughput': 779.83}

06/17/2024 20:43:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.4930, 'learning_rate': 4.0115e-05, 'epoch': 0.88, 'throughput': 780.58}

06/17/2024 20:44:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.4083, 'learning_rate': 3.9268e-05, 'epoch': 0.92, 'throughput': 781.80}

06/17/2024 20:45:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.5172, 'learning_rate': 3.8396e-05, 'epoch': 0.96, 'throughput': 782.01}

06/17/2024 20:46:10 - INFO - llamafactory.extras.callbacks - {'loss': 0.5843, 'learning_rate': 3.7500e-05, 'epoch': 1.00, 'throughput': 782.22}

06/17/2024 20:46:58 - INFO - llamafactory.extras.callbacks - {'loss': 0.4567, 'learning_rate': 3.6582e-05, 'epoch': 1.04, 'throughput': 783.58}

06/17/2024 20:47:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.4180, 'learning_rate': 3.5644e-05, 'epoch': 1.08, 'throughput': 784.96}

06/17/2024 20:48:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.3785, 'learning_rate': 3.4688e-05, 'epoch': 1.12, 'throughput': 783.96}

06/17/2024 20:49:22 - INFO - llamafactory.extras.callbacks - {'loss': 0.4097, 'learning_rate': 3.3714e-05, 'epoch': 1.16, 'throughput': 783.11}

06/17/2024 20:50:09 - INFO - llamafactory.extras.callbacks - {'loss': 0.4507, 'learning_rate': 3.2725e-05, 'epoch': 1.20, 'throughput': 783.25}

06/17/2024 20:51:00 - INFO - llamafactory.extras.callbacks - {'loss': 0.3680, 'learning_rate': 3.1723e-05, 'epoch': 1.24, 'throughput': 782.23}

06/17/2024 20:51:53 - INFO - llamafactory.extras.callbacks - {'loss': 0.4301, 'learning_rate': 3.0709e-05, 'epoch': 1.28, 'throughput': 782.26}

06/17/2024 20:52:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.4488, 'learning_rate': 2.9685e-05, 'epoch': 1.32, 'throughput': 781.89}

06/17/2024 20:53:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.4075, 'learning_rate': 2.8652e-05, 'epoch': 1.36, 'throughput': 781.74}

06/17/2024 20:54:30 - INFO - llamafactory.extras.callbacks - {'loss': 0.4991, 'learning_rate': 2.7613e-05, 'epoch': 1.40, 'throughput': 781.86}

06/17/2024 20:55:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.4894, 'learning_rate': 2.6570e-05, 'epoch': 1.44, 'throughput': 782.49}

06/17/2024 20:56:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.4967, 'learning_rate': 2.5524e-05, 'epoch': 1.48, 'throughput': 782.06}

06/17/2024 20:57:06 - INFO - llamafactory.extras.callbacks - {'loss': 0.5297, 'learning_rate': 2.4476e-05, 'epoch': 1.52, 'throughput': 783.03}

06/17/2024 20:57:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.3939, 'learning_rate': 2.3430e-05, 'epoch': 1.56, 'throughput': 781.82}

06/17/2024 20:58:49 - INFO - llamafactory.extras.callbacks - {'loss': 0.4610, 'learning_rate': 2.2387e-05, 'epoch': 1.60, 'throughput': 781.19}

06/17/2024 20:58:49 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-200

06/17/2024 20:58:50 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/config.json

06/17/2024 20:58:50 - INFO - transformers.configuration_utils - Model config Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}


06/17/2024 20:58:50 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-200/tokenizer_config.json

06/17/2024 20:58:50 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-200/special_tokens_map.json

06/17/2024 20:59:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.4622, 'learning_rate': 2.1348e-05, 'epoch': 1.64, 'throughput': 779.87}

06/17/2024 21:00:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.4043, 'learning_rate': 2.0315e-05, 'epoch': 1.68, 'throughput': 779.61}

06/17/2024 21:01:25 - INFO - llamafactory.extras.callbacks - {'loss': 0.4280, 'learning_rate': 1.9291e-05, 'epoch': 1.72, 'throughput': 779.45}

06/17/2024 21:02:14 - INFO - llamafactory.extras.callbacks - {'loss': 0.3779, 'learning_rate': 1.8277e-05, 'epoch': 1.76, 'throughput': 778.48}

06/17/2024 21:03:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.4526, 'learning_rate': 1.7275e-05, 'epoch': 1.80, 'throughput': 779.26}

06/17/2024 21:03:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.4627, 'learning_rate': 1.6286e-05, 'epoch': 1.84, 'throughput': 779.12}

06/17/2024 21:04:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.4873, 'learning_rate': 1.5312e-05, 'epoch': 1.88, 'throughput': 779.09}

06/17/2024 21:05:40 - INFO - llamafactory.extras.callbacks - {'loss': 0.3234, 'learning_rate': 1.4356e-05, 'epoch': 1.92, 'throughput': 780.05}

06/17/2024 21:06:28 - INFO - llamafactory.extras.callbacks - {'loss': 0.4438, 'learning_rate': 1.3418e-05, 'epoch': 1.96, 'throughput': 780.37}

06/17/2024 21:07:21 - INFO - llamafactory.extras.callbacks - {'loss': 0.4407, 'learning_rate': 1.2500e-05, 'epoch': 2.00, 'throughput': 779.97}

06/17/2024 21:08:15 - INFO - llamafactory.extras.callbacks - {'loss': 0.4401, 'learning_rate': 1.1604e-05, 'epoch': 2.04, 'throughput': 779.51}

06/17/2024 21:09:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.3771, 'learning_rate': 1.0732e-05, 'epoch': 2.08, 'throughput': 780.06}

06/17/2024 21:09:57 - INFO - llamafactory.extras.callbacks - {'loss': 0.4043, 'learning_rate': 9.8850e-06, 'epoch': 2.12, 'throughput': 781.03}

06/17/2024 21:10:42 - INFO - llamafactory.extras.callbacks - {'loss': 0.4018, 'learning_rate': 9.0644e-06, 'epoch': 2.16, 'throughput': 781.14}

06/17/2024 21:11:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.4258, 'learning_rate': 8.2717e-06, 'epoch': 2.20, 'throughput': 781.03}

06/17/2024 21:12:19 - INFO - llamafactory.extras.callbacks - {'loss': 0.3912, 'learning_rate': 7.5084e-06, 'epoch': 2.24, 'throughput': 780.49}

06/17/2024 21:13:06 - INFO - llamafactory.extras.callbacks - {'loss': 0.3458, 'learning_rate': 6.7758e-06, 'epoch': 2.28, 'throughput': 780.17}

06/17/2024 21:13:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.4255, 'learning_rate': 6.0751e-06, 'epoch': 2.32, 'throughput': 780.22}

06/17/2024 21:14:45 - INFO - llamafactory.extras.callbacks - {'loss': 0.4222, 'learning_rate': 5.4077e-06, 'epoch': 2.36, 'throughput': 780.80}

06/17/2024 21:15:33 - INFO - llamafactory.extras.callbacks - {'loss': 0.3990, 'learning_rate': 4.7746e-06, 'epoch': 2.40, 'throughput': 780.45}

06/17/2024 21:15:33 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-300

06/17/2024 21:15:34 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/config.json

06/17/2024 21:15:34 - INFO - transformers.configuration_utils - Model config Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}


06/17/2024 21:15:34 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-300/tokenizer_config.json

06/17/2024 21:15:34 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-300/special_tokens_map.json

06/17/2024 21:16:26 - INFO - llamafactory.extras.callbacks - {'loss': 0.3382, 'learning_rate': 4.1770e-06, 'epoch': 2.44, 'throughput': 780.00}

06/17/2024 21:17:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.4465, 'learning_rate': 3.6159e-06, 'epoch': 2.48, 'throughput': 780.28}

06/17/2024 21:18:13 - INFO - llamafactory.extras.callbacks - {'loss': 0.3250, 'learning_rate': 3.0923e-06, 'epoch': 2.52, 'throughput': 779.93}

06/17/2024 21:19:04 - INFO - llamafactory.extras.callbacks - {'loss': 0.3920, 'learning_rate': 2.6072e-06, 'epoch': 2.56, 'throughput': 779.59}

06/17/2024 21:19:53 - INFO - llamafactory.extras.callbacks - {'loss': 0.3672, 'learning_rate': 2.1614e-06, 'epoch': 2.60, 'throughput': 779.34}

06/17/2024 21:20:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.3554, 'learning_rate': 1.7556e-06, 'epoch': 2.64, 'throughput': 779.07}

06/17/2024 21:21:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.3801, 'learning_rate': 1.3906e-06, 'epoch': 2.68, 'throughput': 778.76}

06/17/2024 21:22:20 - INFO - llamafactory.extras.callbacks - {'loss': 0.4350, 'learning_rate': 1.0670e-06, 'epoch': 2.72, 'throughput': 779.56}

06/17/2024 21:23:15 - INFO - llamafactory.extras.callbacks - {'loss': 0.4063, 'learning_rate': 7.8542e-07, 'epoch': 2.76, 'throughput': 779.43}

06/17/2024 21:24:15 - INFO - llamafactory.extras.callbacks - {'loss': 0.4894, 'learning_rate': 5.4631e-07, 'epoch': 2.80, 'throughput': 779.76}

06/17/2024 21:25:05 - INFO - llamafactory.extras.callbacks - {'loss': 0.3822, 'learning_rate': 3.5010e-07, 'epoch': 2.84, 'throughput': 779.50}

06/17/2024 21:25:57 - INFO - llamafactory.extras.callbacks - {'loss': 0.4028, 'learning_rate': 1.9713e-07, 'epoch': 2.88, 'throughput': 779.46}

06/17/2024 21:26:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.4293, 'learning_rate': 8.7679e-08, 'epoch': 2.92, 'throughput': 779.71}

06/17/2024 21:27:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.4280, 'learning_rate': 2.1929e-08, 'epoch': 2.96, 'throughput': 779.90}

06/17/2024 21:28:29 - INFO - llamafactory.extras.callbacks - {'loss': 0.4766, 'learning_rate': 0.0000e+00, 'epoch': 3.00, 'throughput': 779.83}

06/17/2024 21:28:29 - INFO - transformers.trainer - 

Training completed. Do not forget to share your model on huggingface.co/models =)



06/17/2024 21:28:29 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05

06/17/2024 21:28:30 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-7B-Instruct/snapshots/41c66b0be1c3081f13defc6bdf946c2ef240d6a6/config.json

06/17/2024 21:28:30 - INFO - transformers.configuration_utils - Model config Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}


06/17/2024 21:28:30 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/tokenizer_config.json

06/17/2024 21:28:30 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-7B-Chat/lora/train_2024-06-17-19-49-05/special_tokens_map.json

06/17/2024 21:28:30 - WARNING - llamafactory.extras.ploting - No metric eval_loss to plot.

06/17/2024 21:28:30 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}