infogep commited on
Commit
5b2f259
·
verified ·
1 Parent(s): 0992c37

Delete README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +0 -160
README.md DELETED
@@ -1,160 +0,0 @@
1
- ---
2
- library_name: peft
3
- license: apache-2.0
4
- base_model: 01-ai/Yi-1.5-9B-Chat-16K
5
- tags:
6
- - axolotl
7
- - generated_from_trainer
8
- model-index:
9
- - name: 370986be-947e-47f9-a76a-b396a7a1b383
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: 01-ai/Yi-1.5-9B-Chat-16K
23
- bf16: true
24
- chat_template: llama3
25
- data_processes: 4
26
- dataset_prepared_path: null
27
- datasets:
28
- - data_files:
29
- - 86439f2f93cdf4d4_train_data.json
30
- ds_type: json
31
- format: custom
32
- path: /workspace/input_data/86439f2f93cdf4d4_train_data.json
33
- type:
34
- field_input: input
35
- field_instruction: instruction
36
- field_output: system
37
- format: '{instruction} {input}'
38
- no_input_format: '{instruction}'
39
- system_format: '{system}'
40
- system_prompt: ''
41
- debug: null
42
- deepspeed: null
43
- device_map: auto
44
- do_eval: true
45
- early_stopping_patience: 1
46
- eval_max_new_tokens: 128
47
- eval_steps: 50
48
- eval_table_size: null
49
- evals_per_epoch: null
50
- flash_attention: false
51
- fp16: false
52
- gradient_accumulation_steps: 8
53
- gradient_checkpointing: true
54
- group_by_length: true
55
- hub_model_id: infogep/370986be-947e-47f9-a76a-b396a7a1b383
56
- hub_repo: null
57
- hub_strategy: end
58
- hub_token: null
59
- learning_rate: 0.0005
60
- load_in_4bit: true
61
- load_in_8bit: false
62
- local_rank: null
63
- logging_steps: 10
64
- lora_alpha: 64
65
- lora_dropout: 0.1
66
- lora_fan_in_fan_out: null
67
- lora_model_dir: null
68
- lora_r: 32
69
- lora_target_linear: true
70
- lr_scheduler: cosine
71
- max_grad_norm: 1.5
72
- max_memory:
73
- 0: 80GiB
74
- cpu: 30GiB
75
- max_steps: 150
76
- micro_batch_size: 4
77
- mlflow_experiment_name: /tmp/86439f2f93cdf4d4_train_data.json
78
- model_type: AutoModelForCausalLM
79
- num_epochs: 1
80
- optim_args:
81
- adam_beta1: 0.9
82
- adam_beta2: 0.95
83
- adam_epsilon: 5.0e-05
84
- optimizer: adamw_bnb_8bit
85
- output_dir: miner_id_24
86
- pad_to_sequence_len: true
87
- resume_from_checkpoint: null
88
- s2_attention: null
89
- sample_packing: false
90
- save_steps: 50
91
- sequence_len: 1024
92
- strict: false
93
- tf32: true
94
- tokenizer_type: AutoTokenizer
95
- train_on_inputs: false
96
- trust_remote_code: true
97
- val_set_size: 0.05
98
- wandb_entity: null
99
- wandb_mode: online
100
- wandb_name: ae2946b7-5a83-4c68-97f5-b0524b77f261
101
- wandb_project: cold35
102
- wandb_run: your_name
103
- wandb_runid: ae2946b7-5a83-4c68-97f5-b0524b77f261
104
- warmup_steps: 25
105
- weight_decay: 0.0
106
- xformers_attention: true
107
-
108
- ```
109
-
110
- </details><br>
111
-
112
- # 370986be-947e-47f9-a76a-b396a7a1b383
113
-
114
- This model is a fine-tuned version of [01-ai/Yi-1.5-9B-Chat-16K](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) on the None dataset.
115
- It achieves the following results on the evaluation set:
116
- - Loss: 0.0000
117
-
118
- ## Model description
119
-
120
- More information needed
121
-
122
- ## Intended uses & limitations
123
-
124
- More information needed
125
-
126
- ## Training and evaluation data
127
-
128
- More information needed
129
-
130
- ## Training procedure
131
-
132
- ### Training hyperparameters
133
-
134
- The following hyperparameters were used during training:
135
- - learning_rate: 0.0005
136
- - train_batch_size: 4
137
- - eval_batch_size: 4
138
- - seed: 42
139
- - gradient_accumulation_steps: 8
140
- - total_train_batch_size: 32
141
- - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=5e-05
142
- - lr_scheduler_type: cosine
143
- - lr_scheduler_warmup_steps: 25
144
- - training_steps: 75
145
-
146
- ### Training results
147
-
148
- | Training Loss | Epoch | Step | Validation Loss |
149
- |:-------------:|:------:|:----:|:---------------:|
150
- | No log | 0.0135 | 1 | 0.5385 |
151
- | 0.0 | 0.6734 | 50 | 0.0000 |
152
-
153
-
154
- ### Framework versions
155
-
156
- - PEFT 0.13.2
157
- - Transformers 4.46.0
158
- - Pytorch 2.5.0+cu124
159
- - Datasets 3.0.1
160
- - Tokenizers 0.20.1