munish0838 commited on
Commit
18644ca
1 Parent(s): cd461c1

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +132 -0
README.md ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ base_model: Magpie-Align/Llama-3-8B-WildChat
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Llama-3-8B-WildChat
9
+ results: []
10
+ pipeline_tag: text-generation
11
+ ---
12
+
13
+ # QuantFactory/Llama-3-8B-WildChat-GGUF
14
+ This is quantized version of [Magpie-Align/Llama-3-8B-WildChat](https://huggingface.co/Magpie-Align/Llama-3-8B-WildChat) created using llama.cpp
15
+
16
+ # Model Description
17
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
18
+ <details><summary>See axolotl config</summary>
19
+
20
+ axolotl version: `0.4.0`
21
+ ```yaml
22
+
23
+ base_model: meta-llama/Meta-Llama-3-8B
24
+ model_type: LlamaForCausalLM
25
+ tokenizer_type: AutoTokenizer
26
+
27
+ load_in_8bit: false
28
+ load_in_4bit: false
29
+ strict: false
30
+
31
+ datasets:
32
+ - path: flydust/WildChat_ShareGPT
33
+ type: sharegpt
34
+ conversation: llama3
35
+ dataset_prepared_path: last_run_prepared
36
+ val_set_size: 0.001
37
+ output_dir: ./out_Llama-3-WildChat
38
+
39
+ sequence_len: 8192
40
+ sample_packing: true
41
+ eval_sample_packing: false
42
+ pad_to_sequence_len: true
43
+
44
+ wandb_project: SynDa
45
+ wandb_entity:
46
+ wandb_watch:
47
+ wandb_name: Llama-3-WildChat
48
+ wandb_log_model:
49
+ hub_model_id: SynDa/Llama-3-8B-WildChat
50
+
51
+ gradient_accumulation_steps: 8
52
+ micro_batch_size: 1
53
+ num_epochs: 2
54
+ optimizer: paged_adamw_8bit
55
+ lr_scheduler: cosine
56
+ learning_rate: 2e-5
57
+
58
+ train_on_inputs: false
59
+ group_by_length: false
60
+ bf16: auto
61
+ fp16:
62
+ tf32: false
63
+
64
+ gradient_checkpointing: true
65
+ gradient_checkpointing_kwargs:
66
+ use_reentrant: false
67
+ early_stopping_patience:
68
+ resume_from_checkpoint:
69
+ logging_steps: 1
70
+ xformers_attention:
71
+ flash_attention: true
72
+
73
+ warmup_steps: 100
74
+ evals_per_epoch: 3
75
+ eval_table_size:
76
+ saves_per_epoch: 1
77
+ debug:
78
+ deepspeed:
79
+ weight_decay: 0.0
80
+ fsdp:
81
+ fsdp_config:
82
+ special_tokens:
83
+ pad_token: <|end_of_text|>
84
+
85
+ ```
86
+
87
+ </details><br>
88
+
89
+ # Llama-3-8B-WildChat
90
+
91
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
92
+ It achieves the following results on the evaluation set:
93
+ - Loss: 0.8197
94
+
95
+ ## Training procedure
96
+
97
+ ### Training hyperparameters
98
+
99
+ The following hyperparameters were used during training:
100
+ - learning_rate: 2e-05
101
+ - train_batch_size: 1
102
+ - eval_batch_size: 1
103
+ - seed: 42
104
+ - distributed_type: multi-GPU
105
+ - num_devices: 4
106
+ - gradient_accumulation_steps: 8
107
+ - total_train_batch_size: 32
108
+ - total_eval_batch_size: 4
109
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
110
+ - lr_scheduler_type: cosine
111
+ - lr_scheduler_warmup_steps: 100
112
+ - num_epochs: 2
113
+
114
+ ### Training results
115
+
116
+ | Training Loss | Epoch | Step | Validation Loss |
117
+ |:-------------:|:------:|:----:|:---------------:|
118
+ | 1.1455 | 0.0003 | 1 | 1.3389 |
119
+ | 0.9084 | 0.3333 | 1128 | 0.8551 |
120
+ | 0.9265 | 0.6667 | 2256 | 0.8363 |
121
+ | 0.9086 | 1.0 | 3384 | 0.8210 |
122
+ | 0.8257 | 1.3164 | 4512 | 0.8214 |
123
+ | 0.8306 | 1.6497 | 5640 | 0.8197 |
124
+ | 0.8252 | 1.9831 | 6768 | 0.8197 |
125
+
126
+
127
+ ### Framework versions
128
+
129
+ - Transformers 4.40.2
130
+ - Pytorch 2.3.0+cu121
131
+ - Datasets 2.19.1
132
+ - Tokenizers 0.19.1