lesso commited on
Commit
29d5689
·
verified ·
1 Parent(s): 29e4413

Удаление файла README.md для обновления контента

Browse files
Files changed (1) hide show
  1. README.md +0 -163
README.md DELETED
@@ -1,163 +0,0 @@
1
- ---
2
- library_name: peft
3
- license: apache-2.0
4
- base_model: unsloth/Qwen2-1.5B-Instruct
5
- tags:
6
- - axolotl
7
- - generated_from_trainer
8
- model-index:
9
- - name: 6d5f75df-c0b8-4542-9e67-13e888d5e056
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/Qwen2-1.5B-Instruct
23
- bf16: true
24
- chat_template: llama3
25
- data_processes: 16
26
- dataset_prepared_path: null
27
- datasets:
28
- - data_files:
29
- - 5b484d89c6b37522_train_data.json
30
- ds_type: json
31
- format: custom
32
- path: /workspace/input_data/5b484d89c6b37522_train_data.json
33
- type:
34
- field_input: background
35
- field_instruction: question
36
- field_output: context
37
- format: '{instruction} {input}'
38
- no_input_format: '{instruction}'
39
- system_format: '{system}'
40
- system_prompt: ''
41
- debug: null
42
- deepspeed: null
43
- do_eval: true
44
- early_stopping_patience: 5
45
- eval_batch_size: 4
46
- eval_max_new_tokens: 128
47
- eval_steps: 50
48
- eval_table_size: null
49
- evals_per_epoch: null
50
- flash_attention: true
51
- fp16: false
52
- fsdp: null
53
- fsdp_config: null
54
- gradient_accumulation_steps: 2
55
- gradient_checkpointing: true
56
- group_by_length: true
57
- hub_model_id: lesso/6d5f75df-c0b8-4542-9e67-13e888d5e056
58
- hub_repo: null
59
- hub_strategy: checkpoint
60
- hub_token: null
61
- learning_rate: 0.0001004
62
- load_in_4bit: false
63
- load_in_8bit: false
64
- local_rank: null
65
- logging_steps: 1
66
- lora_alpha: 128
67
- lora_dropout: 0.05
68
- lora_fan_in_fan_out: null
69
- lora_model_dir: null
70
- lora_r: 64
71
- lora_target_linear: true
72
- lr_scheduler: linear
73
- max_grad_norm: 1.0
74
- max_steps: 200
75
- micro_batch_size: 4
76
- mlflow_experiment_name: /tmp/G.O.D/5b484d89c6b37522_train_data.json
77
- model_type: AutoModelForCausalLM
78
- num_epochs: 3
79
- optim_args:
80
- adam_beta1: 0.9
81
- adam_beta2: 0.95
82
- adam_epsilon: 1e-5
83
- optimizer: adamw_bnb_8bit
84
- output_dir: miner_id_24
85
- pad_to_sequence_len: true
86
- resume_from_checkpoint: null
87
- s2_attention: null
88
- sample_packing: false
89
- save_steps: 50
90
- saves_per_epoch: null
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: 9a3de084-2a3b-4eb8-b8aa-9ebfea78476a
101
- wandb_project: new-04
102
- wandb_run: your_name
103
- wandb_runid: 9a3de084-2a3b-4eb8-b8aa-9ebfea78476a
104
- warmup_steps: 10
105
- weight_decay: 0.0
106
- xformers_attention: null
107
-
108
- ```
109
-
110
- </details><br>
111
-
112
- # 6d5f75df-c0b8-4542-9e67-13e888d5e056
113
-
114
- This model is a fine-tuned version of [unsloth/Qwen2-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct) on the None dataset.
115
- It achieves the following results on the evaluation set:
116
- - Loss: 2.0041
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: 0.0001004
136
- - train_batch_size: 4
137
- - eval_batch_size: 4
138
- - seed: 42
139
- - gradient_accumulation_steps: 2
140
- - total_train_batch_size: 8
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=1e-5
142
- - lr_scheduler_type: linear
143
- - lr_scheduler_warmup_steps: 10
144
- - training_steps: 200
145
-
146
- ### Training results
147
-
148
- | Training Loss | Epoch | Step | Validation Loss |
149
- |:-------------:|:------:|:----:|:---------------:|
150
- | 2.123 | 0.0001 | 1 | 2.1501 |
151
- | 2.3991 | 0.0046 | 50 | 2.0390 |
152
- | 1.9699 | 0.0093 | 100 | 2.0185 |
153
- | 2.3666 | 0.0139 | 150 | 2.0085 |
154
- | 2.1299 | 0.0186 | 200 | 2.0041 |
155
-
156
-
157
- ### Framework versions
158
-
159
- - PEFT 0.13.2
160
- - Transformers 4.46.0
161
- - Pytorch 2.5.0+cu124
162
- - Datasets 3.0.1
163
- - Tokenizers 0.20.1