File size: 9,520 Bytes
d4b1108
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
[INFO|2025-03-07 10:08:21] configuration_utils.py:771 >> Model config LlamaConfig {
  "_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 128256
}


[INFO|2025-03-07 10:08:21] tokenization_utils_base.py:2050 >> loading file tokenizer.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/tokenizer.json

[INFO|2025-03-07 10:08:21] tokenization_utils_base.py:2050 >> loading file tokenizer.model from cache at None

[INFO|2025-03-07 10:08:21] tokenization_utils_base.py:2050 >> loading file added_tokens.json from cache at None

[INFO|2025-03-07 10:08:21] tokenization_utils_base.py:2050 >> loading file special_tokens_map.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/special_tokens_map.json

[INFO|2025-03-07 10:08:21] tokenization_utils_base.py:2050 >> loading file tokenizer_config.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/tokenizer_config.json

[INFO|2025-03-07 10:08:21] tokenization_utils_base.py:2050 >> loading file chat_template.jinja from cache at None

[INFO|2025-03-07 10:08:21] tokenization_utils_base.py:2313 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

[INFO|2025-03-07 10:08:22] configuration_utils.py:699 >> loading configuration file config.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/config.json

[INFO|2025-03-07 10:08:22] configuration_utils.py:771 >> Model config LlamaConfig {
  "_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 128256
}


[INFO|2025-03-07 10:08:22] tokenization_utils_base.py:2050 >> loading file tokenizer.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/tokenizer.json

[INFO|2025-03-07 10:08:22] tokenization_utils_base.py:2050 >> loading file tokenizer.model from cache at None

[INFO|2025-03-07 10:08:22] tokenization_utils_base.py:2050 >> loading file added_tokens.json from cache at None

[INFO|2025-03-07 10:08:22] tokenization_utils_base.py:2050 >> loading file special_tokens_map.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/special_tokens_map.json

[INFO|2025-03-07 10:08:22] tokenization_utils_base.py:2050 >> loading file tokenizer_config.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/tokenizer_config.json

[INFO|2025-03-07 10:08:22] tokenization_utils_base.py:2050 >> loading file chat_template.jinja from cache at None

[INFO|2025-03-07 10:08:22] tokenization_utils_base.py:2313 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

[INFO|2025-03-07 10:08:22] logging.py:157 >> Add <|eot_id|>,<|eom_id|> to stop words.

[INFO|2025-03-07 10:08:22] logging.py:157 >> Loading dataset jgayed/ets480...

[INFO|2025-03-07 10:08:27] configuration_utils.py:699 >> loading configuration file config.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/config.json

[INFO|2025-03-07 10:08:27] configuration_utils.py:771 >> Model config LlamaConfig {
  "_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0",
  "use_cache": true,
  "vocab_size": 128256
}


[INFO|2025-03-07 10:08:27] logging.py:157 >> Quantizing model to 4 bit with bitsandbytes.

[INFO|2025-03-07 10:08:27] quantizer_bnb_4bit.py:276 >> The device_map was not initialized. Setting device_map to {'': 0}. If you want to use the model for inference, please set device_map ='auto' 

[INFO|2025-03-07 10:08:27] modeling_utils.py:3982 >> loading weights file model.safetensors from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/model.safetensors.index.json

[INFO|2025-03-07 10:08:27] modeling_utils.py:1633 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.

[INFO|2025-03-07 10:08:27] configuration_utils.py:1140 >> Generate config GenerationConfig {
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ]
}


[INFO|2025-03-07 10:09:51] modeling_utils.py:4970 >> All model checkpoint weights were used when initializing LlamaForCausalLM.


[INFO|2025-03-07 10:09:51] modeling_utils.py:4978 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Llama-3.3-70B-Instruct.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.

[INFO|2025-03-07 10:09:51] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /workspace/hf_home/hub/models--meta-llama--Llama-3.3-70B-Instruct/snapshots/6f6073b423013f6a7d4d9f39144961bfbfbc386b/generation_config.json

[INFO|2025-03-07 10:09:51] configuration_utils.py:1140 >> Generate config GenerationConfig {
  "bos_token_id": 128000,
  "do_sample": true,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "temperature": 0.6,
  "top_p": 0.9
}


[INFO|2025-03-07 10:09:51] logging.py:157 >> Gradient checkpointing enabled.

[INFO|2025-03-07 10:09:51] logging.py:157 >> Using torch SDPA for faster training and inference.

[INFO|2025-03-07 10:09:51] logging.py:157 >> Upcasting trainable params to float32.

[INFO|2025-03-07 10:09:51] logging.py:157 >> Fine-tuning method: LoRA

[INFO|2025-03-07 10:09:51] logging.py:157 >> Found linear modules: up_proj,o_proj,v_proj,q_proj,k_proj,gate_proj,down_proj

[WARNING|2025-03-07 10:09:54] trainer.py:781 >> No label_names provided for model class `PeftModelForCausalLM`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead.

[INFO|2025-03-07 10:09:56] logging.py:157 >> trainable params: 828,375,040 || all params: 276,735,205,376 || trainable%: 0.2993

[INFO|2025-03-07 10:09:56] trainer.py:746 >> Using auto half precision backend

[WARNING|2025-03-07 10:09:56] trainer.py:781 >> No label_names provided for model class `PeftModelForCausalLM`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead.

[INFO|2025-03-07 10:09:56] deepspeed.py:334 >> Detected ZeRO Offload and non-DeepSpeed optimizers: This combination should work as long as the custom optimizer has both CPU and GPU implementation (except LAMB)