tuanna08go commited on
Commit
c7fd434
1 Parent(s): 32fe92c

End of training

Browse files
Files changed (2) hide show
  1. README.md +149 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.1
4
+ base_model: unsloth/Meta-Llama-3.1-8B-Instruct
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 38c537af-903d-4208-9186-707aa28f3a5b
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: unsloth/Meta-Llama-3.1-8B-Instruct
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 66e1f5c3a87b9009_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/66e1f5c3a87b9009_train_data.json
32
+ type:
33
+ field_instruction: file_content
34
+ field_output: extracted_data
35
+ format: '{instruction}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ deepspeed: null
41
+ early_stopping_patience: null
42
+ eval_max_new_tokens: 128
43
+ eval_table_size: null
44
+ evals_per_epoch: 2
45
+ flash_attention: true
46
+ fp16: true
47
+ fsdp: null
48
+ fsdp_config: null
49
+ gradient_accumulation_steps: 1
50
+ gradient_checkpointing: true
51
+ group_by_length: false
52
+ hub_model_id: tuanna08go/38c537af-903d-4208-9186-707aa28f3a5b
53
+ hub_repo: null
54
+ hub_strategy: checkpoint
55
+ hub_token: null
56
+ learning_rate: 0.0001
57
+ load_in_4bit: false
58
+ load_in_8bit: true
59
+ local_rank: null
60
+ logging_steps: 5
61
+ lora_alpha: 32
62
+ lora_dropout: 0.05
63
+ lora_fan_in_fan_out: null
64
+ lora_model_dir: null
65
+ lora_r: 16
66
+ lora_target_linear: true
67
+ lr_scheduler: cosine
68
+ lr_scheduler_warmup_steps: 10
69
+ max_steps: 50
70
+ micro_batch_size: 1
71
+ mlflow_experiment_name: /tmp/66e1f5c3a87b9009_train_data.json
72
+ model_type: AutoModelForCausalLM
73
+ num_epochs: 1
74
+ optimizer: adamw_bnb_8bit
75
+ output_dir: miner_id_24
76
+ pad_to_sequence_len: true
77
+ resume_from_checkpoint: null
78
+ s2_attention: null
79
+ sample_packing: false
80
+ saves_per_epoch: 2
81
+ sequence_len: 2048
82
+ strict: false
83
+ tf32: true
84
+ tokenizer_type: AutoTokenizer
85
+ train_on_inputs: false
86
+ trust_remote_code: true
87
+ val_set_size: 0.1
88
+ wandb_entity: null
89
+ wandb_mode: online
90
+ wandb_name: 38c537af-903d-4208-9186-707aa28f3a5b
91
+ wandb_project: Gradients-On-Demand
92
+ wandb_run: your_name
93
+ wandb_runid: 38c537af-903d-4208-9186-707aa28f3a5b
94
+ warmup_steps: 10
95
+ weight_decay: 0.01
96
+ xformers_attention: true
97
+
98
+ ```
99
+
100
+ </details><br>
101
+
102
+ # 38c537af-903d-4208-9186-707aa28f3a5b
103
+
104
+ This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) on the None dataset.
105
+ It achieves the following results on the evaluation set:
106
+ - Loss: 0.0170
107
+
108
+ ## Model description
109
+
110
+ More information needed
111
+
112
+ ## Intended uses & limitations
113
+
114
+ More information needed
115
+
116
+ ## Training and evaluation data
117
+
118
+ More information needed
119
+
120
+ ## Training procedure
121
+
122
+ ### Training hyperparameters
123
+
124
+ The following hyperparameters were used during training:
125
+ - learning_rate: 0.0001
126
+ - train_batch_size: 1
127
+ - eval_batch_size: 1
128
+ - seed: 42
129
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
130
+ - lr_scheduler_type: cosine
131
+ - lr_scheduler_warmup_steps: 10
132
+ - training_steps: 50
133
+
134
+ ### Training results
135
+
136
+ | Training Loss | Epoch | Step | Validation Loss |
137
+ |:-------------:|:------:|:----:|:---------------:|
138
+ | No log | 0.0006 | 1 | 0.1916 |
139
+ | 0.0114 | 0.0145 | 25 | 0.0221 |
140
+ | 0.0056 | 0.0289 | 50 | 0.0170 |
141
+
142
+
143
+ ### Framework versions
144
+
145
+ - PEFT 0.13.2
146
+ - Transformers 4.46.0
147
+ - Pytorch 2.5.0+cu124
148
+ - Datasets 3.0.1
149
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb5c4822c09d2a78b6e5a749b4189e387e07d74beedbc4b31e1da90f5bb60ccf
3
+ size 167934026