Nexspear commited on
Commit
af18b8e
·
verified ·
1 Parent(s): 9d50e2c

End of training

Browse files
Files changed (2) hide show
  1. README.md +161 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2.5-Math-7B-Instruct
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: bff1d449-34cd-4b99-9213-c545e0868007
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/Qwen2.5-Math-7B-Instruct
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 13f611d881b4973a_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/13f611d881b4973a_train_data.json
32
+ type:
33
+ field_input: sql_context
34
+ field_instruction: sql_prompt
35
+ field_output: sql
36
+ format: '{instruction} {input}'
37
+ no_input_format: '{instruction}'
38
+ system_format: '{system}'
39
+ system_prompt: ''
40
+ debug: null
41
+ deepspeed: null
42
+ early_stopping_patience: null
43
+ eval_max_new_tokens: 128
44
+ eval_table_size: null
45
+ evals_per_epoch: 4
46
+ flash_attention: true
47
+ fp16: null
48
+ fsdp: null
49
+ fsdp_config: null
50
+ gradient_accumulation_steps: 4
51
+ gradient_checkpointing: true
52
+ gradient_clipping: 1.0
53
+ group_by_length: false
54
+ hub_model_id: Nexspear/bff1d449-34cd-4b99-9213-c545e0868007
55
+ hub_repo: null
56
+ hub_strategy: checkpoint
57
+ hub_token: null
58
+ learning_rate: 5.0e-05
59
+ load_in_4bit: false
60
+ load_in_8bit: false
61
+ local_rank: 0
62
+ logging_steps: 3
63
+ lora_alpha: 32
64
+ lora_dropout: 0.05
65
+ lora_fan_in_fan_out: null
66
+ lora_model_dir: null
67
+ lora_r: 16
68
+ lora_target_linear: true
69
+ lr_scheduler: cosine
70
+ max_steps: 400
71
+ micro_batch_size: 8
72
+ mlflow_experiment_name: /tmp/13f611d881b4973a_train_data.json
73
+ model_type: AutoModelForCausalLM
74
+ num_epochs: 3
75
+ optimizer: adamw_bnb_8bit
76
+ output_dir: miner_id_24
77
+ pad_to_sequence_len: true
78
+ resume_from_checkpoint: null
79
+ s2_attention: null
80
+ sample_packing: false
81
+ saves_per_epoch: 4
82
+ sequence_len: 1024
83
+ strict: false
84
+ tf32: false
85
+ tokenizer_type: AutoTokenizer
86
+ train_on_inputs: false
87
+ trust_remote_code: true
88
+ val_set_size: 0.05
89
+ wandb_entity: leixa-personal
90
+ wandb_mode: online
91
+ wandb_name: ad3761c7-9310-40e3-8e3e-842df6723f73
92
+ wandb_project: Gradients-On-Four
93
+ wandb_run: your_name
94
+ wandb_runid: ad3761c7-9310-40e3-8e3e-842df6723f73
95
+ warmup_steps: 10
96
+ weight_decay: 0.01
97
+ xformers_attention: null
98
+
99
+ ```
100
+
101
+ </details><br>
102
+
103
+ # bff1d449-34cd-4b99-9213-c545e0868007
104
+
105
+ This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) on the None dataset.
106
+ It achieves the following results on the evaluation set:
107
+ - Loss: 0.4007
108
+
109
+ ## Model description
110
+
111
+ More information needed
112
+
113
+ ## Intended uses & limitations
114
+
115
+ More information needed
116
+
117
+ ## Training and evaluation data
118
+
119
+ More information needed
120
+
121
+ ## Training procedure
122
+
123
+ ### Training hyperparameters
124
+
125
+ The following hyperparameters were used during training:
126
+ - learning_rate: 5e-05
127
+ - train_batch_size: 8
128
+ - eval_batch_size: 8
129
+ - seed: 42
130
+ - gradient_accumulation_steps: 4
131
+ - total_train_batch_size: 32
132
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
133
+ - lr_scheduler_type: cosine
134
+ - lr_scheduler_warmup_steps: 10
135
+ - training_steps: 400
136
+
137
+ ### Training results
138
+
139
+ | Training Loss | Epoch | Step | Validation Loss |
140
+ |:-------------:|:------:|:----:|:---------------:|
141
+ | No log | 0.0003 | 1 | 2.3533 |
142
+ | 0.9255 | 0.0115 | 34 | 0.8507 |
143
+ | 0.6164 | 0.0229 | 68 | 0.6072 |
144
+ | 0.5464 | 0.0344 | 102 | 0.5226 |
145
+ | 0.5303 | 0.0459 | 136 | 0.4773 |
146
+ | 0.4675 | 0.0573 | 170 | 0.4462 |
147
+ | 0.4969 | 0.0688 | 204 | 0.4305 |
148
+ | 0.4404 | 0.0802 | 238 | 0.4182 |
149
+ | 0.4251 | 0.0917 | 272 | 0.4096 |
150
+ | 0.3919 | 0.1032 | 306 | 0.4044 |
151
+ | 0.4308 | 0.1146 | 340 | 0.4017 |
152
+ | 0.3743 | 0.1261 | 374 | 0.4007 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - PEFT 0.13.2
158
+ - Transformers 4.46.0
159
+ - Pytorch 2.5.0+cu124
160
+ - Datasets 3.0.1
161
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:448512877261a137f3a16a780d17c4ca8eb6e91cacc90751f237cd714bbad85e
3
+ size 161621802