Hugging Face's logo

mrferr3t
/
08668496-5e8f-473f-8969-e5e7f7f05c61

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
mrferr3t commited on
Commit
acc2520
·
verified ·
1 Parent(s): 3d5f419

End of training

Browse files
Files changed (3) hide show
  1. README.md +202 -0
  2. adapter_model.bin +3 -0
  3. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: cc-by-sa-4.0
4
+ base_model: defog/llama-3-sqlcoder-8b
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 08668496-5e8f-473f-8969-e5e7f7f05c61
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
+ auto_find_batch_size: true
23
+ base_model: defog/llama-3-sqlcoder-8b
24
+ bf16: auto
25
+ chat_template: llama3
26
+ dataloader_num_workers: 12
27
+ dataset_prepared_path: null
28
+ datasets:
29
+ - data_files:
30
+ - 4d3ccfd148a48951_train_data.json
31
+ ds_type: json
32
+ format: custom
33
+ path: /workspace/input_data/4d3ccfd148a48951_train_data.json
34
+ type:
35
+ field_instruction: question
36
+ field_output: positive_answer
37
+ format: '{instruction}'
38
+ no_input_format: '{instruction}'
39
+ system_format: '{system}'
40
+ system_prompt: ''
41
+ debug: null
42
+ deepspeed: null
43
+ early_stopping_patience: 3
44
+ early_stopping_threshold: 0.001
45
+ eval_max_new_tokens: 128
46
+ eval_steps: 40
47
+ flash_attention: false
48
+ fp16: null
49
+ fsdp: null
50
+ fsdp_config: null
51
+ gradient_accumulation_steps: 2
52
+ gradient_checkpointing: false
53
+ group_by_length: false
54
+ hub_model_id: mrferr3t/08668496-5e8f-473f-8969-e5e7f7f05c61
55
+ hub_repo: null
56
+ hub_strategy: checkpoint
57
+ hub_token: null
58
+ learning_rate: 0.0003
59
+ load_in_4bit: false
60
+ load_in_8bit: false
61
+ local_rank: null
62
+ logging_steps: 100
63
+ lora_alpha: 16
64
+ lora_dropout: 0.05
65
+ lora_fan_in_fan_out: null
66
+ lora_model_dir: null
67
+ lora_r: 8
68
+ lora_target_linear: true
69
+ lr_scheduler: cosine
70
+ micro_batch_size: 32
71
+ mlflow_experiment_name: /tmp/4d3ccfd148a48951_train_data.json
72
+ model_type: AutoModelForCausalLM
73
+ num_epochs: 50
74
+ optimizer: adamw_bnb_8bit
75
+ output_dir: miner_id_24
76
+ pad_to_sequence_len: true
77
+ s2_attention: null
78
+ sample_packing: false
79
+ save_steps: 40
80
+ saves_per_epoch: 0
81
+ sequence_len: 512
82
+ special_tokens:
83
+ pad_token: <|eot_id|>
84
+ strict: false
85
+ tf32: false
86
+ tokenizer_type: AutoTokenizer
87
+ train_on_inputs: false
88
+ trust_remote_code: true
89
+ val_set_size: 0.02
90
+ wandb_entity: null
91
+ wandb_mode: online
92
+ wandb_name: fbae069e-fb6e-483d-98a1-0b88f4497a85
93
+ wandb_project: Gradients-On-Demand
94
+ wandb_run: your_name
95
+ wandb_runid: fbae069e-fb6e-483d-98a1-0b88f4497a85
96
+ warmup_ratio: 0.05
97
+ weight_decay: 0.0
98
+ xformers_attention: null
99
+
100
+ ```
101
+
102
+ </details><br>
103
+
104
+ # 08668496-5e8f-473f-8969-e5e7f7f05c61
105
+
106
+ This model is a fine-tuned version of [defog/llama-3-sqlcoder-8b](https://huggingface.co/defog/llama-3-sqlcoder-8b) on the None dataset.
107
+ It achieves the following results on the evaluation set:
108
+ - Loss: 0.6502
109
+
110
+ ## Model description
111
+
112
+ More information needed
113
+
114
+ ## Intended uses & limitations
115
+
116
+ More information needed
117
+
118
+ ## Training and evaluation data
119
+
120
+ More information needed
121
+
122
+ ## Training procedure
123
+
124
+ ### Training hyperparameters
125
+
126
+ The following hyperparameters were used during training:
127
+ - learning_rate: 0.0003
128
+ - train_batch_size: 32
129
+ - eval_batch_size: 32
130
+ - seed: 42
131
+ - gradient_accumulation_steps: 2
132
+ - total_train_batch_size: 64
133
+ - optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
134
+ - lr_scheduler_type: cosine
135
+ - lr_scheduler_warmup_steps: 449
136
+ - num_epochs: 50
137
+
138
+ ### Training results
139
+
140
+ | Training Loss | Epoch | Step | Validation Loss |
141
+ |:-------------:|:------:|:----:|:---------------:|
142
+ | No log | 0.0007 | 1 | 1.2115 |
143
+ | No log | 0.0278 | 40 | 1.0597 |
144
+ | No log | 0.0556 | 80 | 0.9304 |
145
+ | 1.0735 | 0.0833 | 120 | 0.8850 |
146
+ | 1.0735 | 0.1111 | 160 | 0.8702 |
147
+ | 0.8708 | 0.1389 | 200 | 0.8522 |
148
+ | 0.8708 | 0.1667 | 240 | 0.8398 |
149
+ | 0.8708 | 0.1944 | 280 | 0.8326 |
150
+ | 0.8352 | 0.2222 | 320 | 0.8218 |
151
+ | 0.8352 | 0.25 | 360 | 0.8126 |
152
+ | 0.8303 | 0.2778 | 400 | 0.8182 |
153
+ | 0.8303 | 0.3056 | 440 | 0.8048 |
154
+ | 0.8303 | 0.3333 | 480 | 0.8074 |
155
+ | 0.831 | 0.3611 | 520 | 0.7934 |
156
+ | 0.831 | 0.3889 | 560 | 0.7838 |
157
+ | 0.7971 | 0.4167 | 600 | 0.7793 |
158
+ | 0.7971 | 0.4444 | 640 | 0.7775 |
159
+ | 0.7971 | 0.4722 | 680 | 0.7648 |
160
+ | 0.7748 | 0.5 | 720 | 0.7571 |
161
+ | 0.7748 | 0.5278 | 760 | 0.7516 |
162
+ | 0.7664 | 0.5556 | 800 | 0.7503 |
163
+ | 0.7664 | 0.5833 | 840 | 0.7475 |
164
+ | 0.7664 | 0.6111 | 880 | 0.7394 |
165
+ | 0.7595 | 0.6389 | 920 | 0.7341 |
166
+ | 0.7595 | 0.6667 | 960 | 0.7318 |
167
+ | 0.7373 | 0.6944 | 1000 | 0.7329 |
168
+ | 0.7373 | 0.7222 | 1040 | 0.7273 |
169
+ | 0.7373 | 0.75 | 1080 | 0.7231 |
170
+ | 0.7192 | 0.7778 | 1120 | 0.7199 |
171
+ | 0.7192 | 0.8056 | 1160 | 0.7076 |
172
+ | 0.727 | 0.8333 | 1200 | 0.7006 |
173
+ | 0.727 | 0.8611 | 1240 | 0.6935 |
174
+ | 0.727 | 0.8889 | 1280 | 0.6962 |
175
+ | 0.7096 | 0.9167 | 1320 | 0.6902 |
176
+ | 0.7096 | 0.9444 | 1360 | 0.6879 |
177
+ | 0.6914 | 0.9722 | 1400 | 0.6850 |
178
+ | 0.6914 | 1.0 | 1440 | 0.6824 |
179
+ | 0.6914 | 1.0278 | 1480 | 0.6757 |
180
+ | 0.6123 | 1.0556 | 1520 | 0.6694 |
181
+ | 0.6123 | 1.0833 | 1560 | 0.6713 |
182
+ | 0.5842 | 1.1111 | 1600 | 0.6688 |
183
+ | 0.5842 | 1.1389 | 1640 | 0.6696 |
184
+ | 0.5842 | 1.1667 | 1680 | 0.6716 |
185
+ | 0.6055 | 1.1944 | 1720 | 0.6644 |
186
+ | 0.6055 | 1.2222 | 1760 | 0.6659 |
187
+ | 0.5986 | 1.25 | 1800 | 0.6627 |
188
+ | 0.5986 | 1.2778 | 1840 | 0.6571 |
189
+ | 0.5986 | 1.3056 | 1880 | 0.6509 |
190
+ | 0.5943 | 1.3333 | 1920 | 0.6492 |
191
+ | 0.5943 | 1.3611 | 1960 | 0.6528 |
192
+ | 0.5999 | 1.3889 | 2000 | 0.6494 |
193
+ | 0.5999 | 1.4167 | 2040 | 0.6502 |
194
+
195
+
196
+ ### Framework versions
197
+
198
+ - PEFT 0.13.2
199
+ - Transformers 4.46.0
200
+ - Pytorch 2.3.1+cu121
201
+ - Datasets 3.0.1
202
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:013253bbc1f5a4f87b35820d06069bc389bef3c97382e8e8bffb0ca26dd989c1
3
+ size 84047370
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f1308f92a5930d7c9bb0e6f7a23b8ab7f031173ea49959a38210dbd1968952b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac03db51f9af3c585c60a4c454b37f6061aaf411dadfbb2acf208aa2f28838b6
3
  size 83945296