Hugging Face's logo

tuantmdev
/
08ad529c-12b5-4748-b0b2-fdd63cf52842

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuantmdev commited on
Commit
5245b02
·
verified ·
1 Parent(s): a20cf96

End of training

Browse files
Files changed (3) hide show
  1. README.md +157 -0
  2. adapter_model.bin +3 -0
  3. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: teknium/OpenHermes-2.5-Mistral-7B
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 08ad529c-12b5-4748-b0b2-fdd63cf52842
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: teknium/OpenHermes-2.5-Mistral-7B
24
+ bf16: auto
25
+ chat_template: llama3
26
+ dataset_prepared_path: null
27
+ datasets:
28
+ - data_files:
29
+ - 7d41eb876534c0fd_train_data.json
30
+ ds_type: json
31
+ format: custom
32
+ path: /workspace/input_data/7d41eb876534c0fd_train_data.json
33
+ type:
34
+ field_instruction: question
35
+ field_output: answer
36
+ format: '{instruction}'
37
+ no_input_format: '{instruction}'
38
+ system_format: '{system}'
39
+ system_prompt: ''
40
+ debug: null
41
+ deepspeed: null
42
+ early_stopping_patience: 3
43
+ eval_max_new_tokens: 128
44
+ eval_steps: 50
45
+ eval_table_size: null
46
+ flash_attention: true
47
+ fp16: null
48
+ fsdp: null
49
+ fsdp_config: null
50
+ gradient_accumulation_steps: 8
51
+ gradient_checkpointing: false
52
+ group_by_length: true
53
+ hub_model_id: tuantmdev/08ad529c-12b5-4748-b0b2-fdd63cf52842
54
+ hub_repo: null
55
+ hub_strategy: checkpoint
56
+ hub_token: null
57
+ learning_rate: 1e-4
58
+ load_in_4bit: false
59
+ load_in_8bit: false
60
+ local_rank: null
61
+ logging_steps: 40
62
+ lora_alpha: 64
63
+ lora_dropout: 0.05
64
+ lora_fan_in_fan_out: null
65
+ lora_model_dir: null
66
+ lora_r: 32
67
+ lora_target_linear: true
68
+ lr_scheduler: cosine
69
+ max_grad_norm: 1.0
70
+ max_steps: 400
71
+ micro_batch_size: 2
72
+ mlflow_experiment_name: /tmp/7d41eb876534c0fd_train_data.json
73
+ model_type: AutoModelForCausalLM
74
+ num_epochs: 1
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
+ save_steps: 50
82
+ save_strategy: steps
83
+ sequence_len: 512
84
+ special_tokens:
85
+ pad_token: <|im_end|>
86
+ strict: false
87
+ tf32: false
88
+ tokenizer_type: AutoTokenizer
89
+ train_on_inputs: false
90
+ trust_remote_code: true
91
+ val_set_size: 0.05
92
+ wandb_entity: null
93
+ wandb_mode: online
94
+ wandb_name: 496791d3-1072-47bf-b27c-12b2b1def570
95
+ wandb_project: Gradients-On-Demand
96
+ wandb_run: unknown
97
+ wandb_runid: 496791d3-1072-47bf-b27c-12b2b1def570
98
+ warmup_steps: 80
99
+ weight_decay: 0.0
100
+ xformers_attention: null
101
+
102
+ ```
103
+
104
+ </details><br>
105
+
106
+ # 08ad529c-12b5-4748-b0b2-fdd63cf52842
107
+
108
+ This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on the None dataset.
109
+ It achieves the following results on the evaluation set:
110
+ - Loss: 0.1680
111
+
112
+ ## Model description
113
+
114
+ More information needed
115
+
116
+ ## Intended uses & limitations
117
+
118
+ More information needed
119
+
120
+ ## Training and evaluation data
121
+
122
+ More information needed
123
+
124
+ ## Training procedure
125
+
126
+ ### Training hyperparameters
127
+
128
+ The following hyperparameters were used during training:
129
+ - learning_rate: 0.0001
130
+ - train_batch_size: 2
131
+ - eval_batch_size: 2
132
+ - seed: 42
133
+ - gradient_accumulation_steps: 8
134
+ - total_train_batch_size: 16
135
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
136
+ - lr_scheduler_type: cosine
137
+ - lr_scheduler_warmup_steps: 80
138
+ - training_steps: 400
139
+
140
+ ### Training results
141
+
142
+ | Training Loss | Epoch | Step | Validation Loss |
143
+ |:-------------:|:------:|:----:|:---------------:|
144
+ | No log | 0.0003 | 1 | 0.1955 |
145
+ | 1.0317 | 0.0169 | 50 | 0.1430 |
146
+ | 1.0357 | 0.0339 | 100 | 0.1662 |
147
+ | 1.1557 | 0.0508 | 150 | 0.1642 |
148
+ | 1.2253 | 0.0678 | 200 | 0.1680 |
149
+
150
+
151
+ ### Framework versions
152
+
153
+ - PEFT 0.13.2
154
+ - Transformers 4.46.0
155
+ - Pytorch 2.5.0+cu124
156
+ - Datasets 3.0.1
157
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ccbe4f1d1d0913d74781c41fff41e27d8eb570ca04f4501e2a2ebb18be09574
3
+ size 335706186
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2c5c0d015035441f62b2f1b2f504b13db0c2cc6d40462ccfcb1cf7a2f546928
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85c7805f10a61f75399195d1b2b6dd77998ecabb82661f38086caf5ce16f9c19
3
  size 335604696