Hugging Face's logo

Alphatao
/
8783abb4-4863-4d35-96d0-38591b2d8490

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
Alphatao commited on
Commit
be203af
·
verified ·
1 Parent(s): ed466e8

End of training

Browse files
Files changed (3) hide show
  1. README.md +207 -0
  2. adapter_model.bin +3 -0
  3. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2-0.5B-Instruct
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 8783abb4-4863-4d35-96d0-38591b2d8490
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.4.1`
20
+ ```yaml
21
+ adapter: lora
22
+ base_model: Qwen/Qwen2-0.5B-Instruct
23
+ bf16: true
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - a23a73113e5bcd49_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/a23a73113e5bcd49_train_data.json
32
+ type:
33
+ field_instruction: title
34
+ field_output: content
35
+ format: '{instruction}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ device_map:
41
+ ? ''
42
+ : 0,1,2,3,4,5,6,7
43
+ early_stopping_patience: 2
44
+ eval_max_new_tokens: 128
45
+ eval_steps: 100
46
+ eval_table_size: null
47
+ flash_attention: true
48
+ gradient_accumulation_steps: 8
49
+ gradient_checkpointing: true
50
+ group_by_length: false
51
+ hub_model_id: Alphatao/8783abb4-4863-4d35-96d0-38591b2d8490
52
+ hub_repo: null
53
+ hub_strategy: null
54
+ hub_token: null
55
+ learning_rate: 0.0002
56
+ load_best_model_at_end: true
57
+ load_in_4bit: false
58
+ load_in_8bit: false
59
+ local_rank: null
60
+ logging_steps: 1
61
+ lora_alpha: 128
62
+ lora_dropout: 0.1
63
+ lora_fan_in_fan_out: null
64
+ lora_model_dir: null
65
+ lora_r: 64
66
+ lora_target_linear: true
67
+ lora_target_modules:
68
+ - q_proj
69
+ - k_proj
70
+ - v_proj
71
+ - o_proj
72
+ lr_scheduler: cosine
73
+ max_grad_norm: 1.0
74
+ max_steps: 5376
75
+ micro_batch_size: 4
76
+ mlflow_experiment_name: /tmp/a23a73113e5bcd49_train_data.json
77
+ model_type: AutoModelForCausalLM
78
+ num_epochs: 2
79
+ optimizer: adamw_bnb_8bit
80
+ output_dir: miner_id_24
81
+ pad_to_sequence_len: true
82
+ resume_from_checkpoint: null
83
+ s2_attention: null
84
+ sample_packing: false
85
+ save_steps: 100
86
+ sequence_len: 1024
87
+ strict: false
88
+ tf32: true
89
+ tokenizer_type: AutoTokenizer
90
+ train_on_inputs: false
91
+ trust_remote_code: true
92
+ val_set_size: 0.04787437763309077
93
+ wandb_entity: null
94
+ wandb_mode: online
95
+ wandb_name: 032a2798-2e45-4672-ba51-e28a8f853060
96
+ wandb_project: Gradients-On-Demand
97
+ wandb_run: your_name
98
+ wandb_runid: 032a2798-2e45-4672-ba51-e28a8f853060
99
+ warmup_steps: 10
100
+ weight_decay: 0.0
101
+ xformers_attention: null
102
+
103
+ ```
104
+
105
+ </details><br>
106
+
107
+ # 8783abb4-4863-4d35-96d0-38591b2d8490
108
+
109
+ This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the None dataset.
110
+ It achieves the following results on the evaluation set:
111
+ - Loss: 1.7221
112
+
113
+ ## Model description
114
+
115
+ More information needed
116
+
117
+ ## Intended uses & limitations
118
+
119
+ More information needed
120
+
121
+ ## Training and evaluation data
122
+
123
+ More information needed
124
+
125
+ ## Training procedure
126
+
127
+ ### Training hyperparameters
128
+
129
+ The following hyperparameters were used during training:
130
+ - learning_rate: 0.0002
131
+ - train_batch_size: 4
132
+ - eval_batch_size: 4
133
+ - seed: 42
134
+ - gradient_accumulation_steps: 8
135
+ - total_train_batch_size: 32
136
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
137
+ - lr_scheduler_type: cosine
138
+ - lr_scheduler_warmup_steps: 10
139
+ - training_steps: 5376
140
+
141
+ ### Training results
142
+
143
+ | Training Loss | Epoch | Step | Validation Loss |
144
+ |:-------------:|:------:|:----:|:---------------:|
145
+ | 2.7661 | 0.0003 | 1 | 2.7781 |
146
+ | 2.4133 | 0.0322 | 100 | 2.3111 |
147
+ | 2.3796 | 0.0644 | 200 | 2.2424 |
148
+ | 2.1234 | 0.0965 | 300 | 2.2007 |
149
+ | 2.2836 | 0.1287 | 400 | 2.1683 |
150
+ | 2.1882 | 0.1609 | 500 | 2.1389 |
151
+ | 2.1209 | 0.1931 | 600 | 2.1168 |
152
+ | 1.9807 | 0.2253 | 700 | 2.0961 |
153
+ | 2.0003 | 0.2574 | 800 | 2.0819 |
154
+ | 1.8976 | 0.2896 | 900 | 2.0609 |
155
+ | 2.2535 | 0.3218 | 1000 | 2.0465 |
156
+ | 2.0813 | 0.3540 | 1100 | 2.0284 |
157
+ | 2.0837 | 0.3862 | 1200 | 2.0134 |
158
+ | 1.8759 | 0.4183 | 1300 | 2.0016 |
159
+ | 2.0767 | 0.4505 | 1400 | 1.9873 |
160
+ | 2.0557 | 0.4827 | 1500 | 1.9745 |
161
+ | 1.708 | 0.5149 | 1600 | 1.9607 |
162
+ | 2.0113 | 0.5471 | 1700 | 1.9480 |
163
+ | 2.0235 | 0.5792 | 1800 | 1.9328 |
164
+ | 1.9351 | 0.6114 | 1900 | 1.9223 |
165
+ | 1.796 | 0.6436 | 2000 | 1.9164 |
166
+ | 1.8088 | 0.6758 | 2100 | 1.9011 |
167
+ | 1.6286 | 0.7080 | 2200 | 1.8900 |
168
+ | 1.9361 | 0.7401 | 2300 | 1.8786 |
169
+ | 1.636 | 0.7723 | 2400 | 1.8669 |
170
+ | 1.8454 | 0.8045 | 2500 | 1.8579 |
171
+ | 1.9547 | 0.8367 | 2600 | 1.8472 |
172
+ | 1.5638 | 0.8689 | 2700 | 1.8384 |
173
+ | 1.611 | 0.9010 | 2800 | 1.8275 |
174
+ | 1.7571 | 0.9332 | 2900 | 1.8143 |
175
+ | 1.9847 | 0.9654 | 3000 | 1.8063 |
176
+ | 1.9508 | 0.9976 | 3100 | 1.7982 |
177
+ | 1.3798 | 1.0298 | 3200 | 1.7971 |
178
+ | 1.5009 | 1.0619 | 3300 | 1.7864 |
179
+ | 1.5614 | 1.0941 | 3400 | 1.7795 |
180
+ | 1.7675 | 1.1263 | 3500 | 1.7721 |
181
+ | 1.2293 | 1.1585 | 3600 | 1.7665 |
182
+ | 1.7646 | 1.1907 | 3700 | 1.7610 |
183
+ | 1.4301 | 1.2228 | 3800 | 1.7582 |
184
+ | 1.2718 | 1.2550 | 3900 | 1.7507 |
185
+ | 1.6806 | 1.2872 | 4000 | 1.7457 |
186
+ | 1.5779 | 1.3194 | 4100 | 1.7413 |
187
+ | 1.3326 | 1.3516 | 4200 | 1.7374 |
188
+ | 1.6239 | 1.3837 | 4300 | 1.7350 |
189
+ | 1.713 | 1.4159 | 4400 | 1.7322 |
190
+ | 1.5364 | 1.4481 | 4500 | 1.7300 |
191
+ | 1.2966 | 1.4803 | 4600 | 1.7277 |
192
+ | 1.5881 | 1.5125 | 4700 | 1.7258 |
193
+ | 1.2867 | 1.5447 | 4800 | 1.7244 |
194
+ | 1.6141 | 1.5768 | 4900 | 1.7233 |
195
+ | 1.6782 | 1.6090 | 5000 | 1.7233 |
196
+ | 1.7381 | 1.6412 | 5100 | 1.7224 |
197
+ | 1.6309 | 1.6734 | 5200 | 1.7222 |
198
+ | 1.6214 | 1.7056 | 5300 | 1.7221 |
199
+
200
+
201
+ ### Framework versions
202
+
203
+ - PEFT 0.13.2
204
+ - Transformers 4.46.0
205
+ - Pytorch 2.5.0+cu124
206
+ - Datasets 3.0.1
207
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d35142ff14a651d0437865bcab6173c5384c4a5d2c8169a47d5966855027fc
3
+ size 140892234
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb6c0dacc45465990bad8f4ce8c0ed7721414eac5cdc77a95a1f7449b485fcf9
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c326132b5c5343116909838656613a0aed1d4fc34e166c8ca5ba3a366e866af
3
  size 140815952