File size: 11,439 Bytes
21af751 |
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 |
[INFO|2025-02-22 11:20:55] configuration_utils.py:696 >> loading configuration file config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\config.json
[INFO|2025-02-22 11:20:55] configuration_utils.py:768 >> Model config Qwen2Config {
"_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file vocab.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\vocab.json
[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file merges.txt from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\merges.txt
[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\tokenizer.json
[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\tokenizer_config.json
[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
[INFO|2025-02-22 11:20:55] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[INFO|2025-02-22 11:20:56] configuration_utils.py:696 >> loading configuration file config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\config.json
[INFO|2025-02-22 11:20:56] configuration_utils.py:768 >> Model config Qwen2Config {
"_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file vocab.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\vocab.json
[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file merges.txt from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\merges.txt
[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\tokenizer.json
[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at None
[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\tokenizer_config.json
[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
[INFO|2025-02-22 11:20:56] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[INFO|2025-02-22 11:20:56] logging.py:157 >> Add <|im_end|> to stop words.
[INFO|2025-02-22 11:20:56] logging.py:157 >> Loading dataset prithivMLmods/Deepthink-Reasoning-Ins...
[INFO|2025-02-22 11:21:19] logging.py:157 >> Loading dataset open-thoughts/OpenThoughts-114k...
[INFO|2025-02-22 11:27:18] configuration_utils.py:696 >> loading configuration file config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\config.json
[INFO|2025-02-22 11:27:18] configuration_utils.py:768 >> Model config Qwen2Config {
"_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
[INFO|2025-02-22 11:27:18] modeling_utils.py:3904 >> loading weights file model.safetensors from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\model.safetensors
[INFO|2025-02-22 11:27:18] modeling_utils.py:1582 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
[INFO|2025-02-22 11:27:18] configuration_utils.py:1140 >> Generate config GenerationConfig {
"bos_token_id": 151643,
"eos_token_id": 151645
}
[INFO|2025-02-22 11:27:21] modeling_utils.py:4888 >> All model checkpoint weights were used when initializing Qwen2ForCausalLM.
[INFO|2025-02-22 11:27:21] modeling_utils.py:4896 >> All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2.5-0.5B-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.
[INFO|2025-02-22 11:27:22] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at C:\Users\Asad_\.cache\huggingface\hub\models--Qwen--Qwen2.5-0.5B-Instruct\snapshots\7ae557604adf67be50417f59c2c2f167def9a775\generation_config.json
[INFO|2025-02-22 11:27:22] configuration_utils.py:1140 >> Generate config GenerationConfig {
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
}
[INFO|2025-02-22 11:27:22] logging.py:157 >> Gradient checkpointing enabled.
[INFO|2025-02-22 11:27:22] logging.py:157 >> Using torch SDPA for faster training and inference.
[INFO|2025-02-22 11:27:22] logging.py:157 >> Upcasting trainable params to float32.
[INFO|2025-02-22 11:27:22] logging.py:157 >> Fine-tuning method: Full
[INFO|2025-02-22 11:27:22] logging.py:157 >> trainable params: 494,032,768 || all params: 494,032,768 || trainable%: 100.0000
[INFO|2025-02-22 11:27:22] trainer.py:741 >> Using auto half precision backend
[INFO|2025-02-22 11:27:22] trainer.py:2775 >> Loading model from saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\checkpoint-13000.
[WARNING|2025-02-22 11:27:23] trainer.py:3018 >> There were missing keys in the checkpoint model loaded: ['lm_head.weight'].
[INFO|2025-02-22 11:27:23] trainer.py:2369 >> ***** Running training *****
[INFO|2025-02-22 11:27:23] trainer.py:2370 >> Num examples = 102,787
[INFO|2025-02-22 11:27:23] trainer.py:2371 >> Num Epochs = 1
[INFO|2025-02-22 11:27:23] trainer.py:2372 >> Instantaneous batch size per device = 1
[INFO|2025-02-22 11:27:23] trainer.py:2375 >> Total train batch size (w. parallel, distributed & accumulation) = 8
[INFO|2025-02-22 11:27:23] trainer.py:2376 >> Gradient Accumulation steps = 8
[INFO|2025-02-22 11:27:23] trainer.py:2377 >> Total optimization steps = 12,848
[INFO|2025-02-22 11:27:23] trainer.py:2378 >> Number of trainable parameters = 494,032,768
[INFO|2025-02-22 11:27:23] trainer.py:2400 >> Continuing training from checkpoint, will skip to saved global_step
[INFO|2025-02-22 11:27:23] trainer.py:2401 >> Continuing training from epoch 1
[INFO|2025-02-22 11:27:23] trainer.py:2402 >> Continuing training from global step 13000
[INFO|2025-02-22 11:27:23] trainer.py:2404 >> Will skip the first 1 epochs then the first 1216 batches in the first epoch.
[INFO|2025-02-22 11:27:23] trainer.py:2643 >>
Training completed. Do not forget to share your model on huggingface.co/models =)
[INFO|2025-02-22 11:27:23] trainer.py:3910 >> Saving model checkpoint to saves\Qwen2.5-0.5B-Instruct\full\20-02-2025
[INFO|2025-02-22 11:27:23] configuration_utils.py:420 >> Configuration saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\config.json
[INFO|2025-02-22 11:27:23] configuration_utils.py:909 >> Configuration saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\generation_config.json
[INFO|2025-02-22 11:27:25] modeling_utils.py:2988 >> Model weights saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\model.safetensors
[INFO|2025-02-22 11:27:25] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\tokenizer_config.json
[INFO|2025-02-22 11:27:25] tokenization_utils_base.py:2500 >> Special tokens file saved in saves\Qwen2.5-0.5B-Instruct\full\20-02-2025\special_tokens_map.json
[WARNING|2025-02-22 11:27:26] logging.py:162 >> No metric eval_accuracy to plot.
[INFO|2025-02-22 11:27:26] trainer.py:4226 >>
***** Running Evaluation *****
[INFO|2025-02-22 11:27:26] trainer.py:4228 >> Num examples = 11421
[INFO|2025-02-22 11:27:26] trainer.py:4231 >> Batch size = 1
|