lesso commited on
Commit
b436ea2
1 Parent(s): 7d5fc95

End of training

Browse files
Files changed (2) hide show
  1. README.md +147 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/Yarn-Llama-2-7b-64k
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: 0333da37-65b7-4e2e-a8ab-dd03a4412253
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ adapter: lora
21
+ base_model: NousResearch/Yarn-Llama-2-7b-64k
22
+ bf16: false
23
+ chat_template: llama3
24
+ datasets:
25
+ - data_files:
26
+ - 4935ce82c18c2a92_train_data.json
27
+ ds_type: json
28
+ format: custom
29
+ path: /workspace/input_data/4935ce82c18c2a92_train_data.json
30
+ type:
31
+ field_input: code
32
+ field_instruction: instruction
33
+ field_output: output
34
+ format: '{instruction} {input}'
35
+ no_input_format: '{instruction}'
36
+ system_format: '{system}'
37
+ system_prompt: ''
38
+ debug: null
39
+ deepspeed: null
40
+ early_stopping_patience: null
41
+ eval_max_new_tokens: 128
42
+ eval_table_size: null
43
+ evals_per_epoch: 1
44
+ flash_attention: false
45
+ fp16: true
46
+ fsdp: null
47
+ fsdp_config: null
48
+ gradient_accumulation_steps: 4
49
+ gradient_checkpointing: true
50
+ group_by_length: false
51
+ hub_model_id: lesso/0333da37-65b7-4e2e-a8ab-dd03a4412253
52
+ hub_repo: null
53
+ hub_strategy: checkpoint
54
+ hub_token: null
55
+ learning_rate: 0.0002
56
+ load_in_4bit: false
57
+ load_in_8bit: false
58
+ local_rank: null
59
+ logging_steps: 1
60
+ lora_alpha: 16
61
+ lora_dropout: 0.05
62
+ lora_fan_in_fan_out: null
63
+ lora_model_dir: null
64
+ lora_r: 8
65
+ lora_target_linear: true
66
+ lr_scheduler: cosine
67
+ max_steps: 1000
68
+ micro_batch_size: 1
69
+ mlflow_experiment_name: /tmp/4935ce82c18c2a92_train_data.json
70
+ model_type: AutoModelForCausalLM
71
+ num_epochs: 1
72
+ optimizer: adamw_hf
73
+ output_dir: miner_id_24
74
+ pad_to_sequence_len: true
75
+ resume_from_checkpoint: null
76
+ s2_attention: null
77
+ sample_packing: false
78
+ saves_per_epoch: 1
79
+ sequence_len: 1024
80
+ strict: false
81
+ tf32: false
82
+ tokenizer_type: AutoTokenizer
83
+ train_on_inputs: false
84
+ trust_remote_code: true
85
+ val_set_size: 0.05
86
+ wandb_entity: null
87
+ wandb_mode: online
88
+ wandb_name: 0333da37-65b7-4e2e-a8ab-dd03a4412253
89
+ wandb_project: Gradients-On-Demand
90
+ wandb_run: your_name
91
+ wandb_runid: 0333da37-65b7-4e2e-a8ab-dd03a4412253
92
+ warmup_steps: 0
93
+ weight_decay: 0.0
94
+ xformers_attention: null
95
+
96
+ ```
97
+
98
+ </details><br>
99
+
100
+ # 0333da37-65b7-4e2e-a8ab-dd03a4412253
101
+
102
+ This model is a fine-tuned version of [NousResearch/Yarn-Llama-2-7b-64k](https://huggingface.co/NousResearch/Yarn-Llama-2-7b-64k) on the None dataset.
103
+ It achieves the following results on the evaluation set:
104
+ - Loss: 0.0001
105
+
106
+ ## Model description
107
+
108
+ More information needed
109
+
110
+ ## Intended uses & limitations
111
+
112
+ More information needed
113
+
114
+ ## Training and evaluation data
115
+
116
+ More information needed
117
+
118
+ ## Training procedure
119
+
120
+ ### Training hyperparameters
121
+
122
+ The following hyperparameters were used during training:
123
+ - learning_rate: 0.0002
124
+ - train_batch_size: 1
125
+ - eval_batch_size: 1
126
+ - seed: 42
127
+ - gradient_accumulation_steps: 4
128
+ - total_train_batch_size: 4
129
+ - optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
130
+ - lr_scheduler_type: cosine
131
+ - training_steps: 1000
132
+ - mixed_precision_training: Native AMP
133
+
134
+ ### Training results
135
+
136
+ | Training Loss | Epoch | Step | Validation Loss |
137
+ |:-------------:|:------:|:----:|:---------------:|
138
+ | 0.0001 | 0.0358 | 1000 | 0.0001 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - PEFT 0.13.2
144
+ - Transformers 4.46.0
145
+ - Pytorch 2.5.0+cu124
146
+ - Datasets 3.0.1
147
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccba190efd8b1e63d8dbca8167bbb18c6f2cf052434acec0751966b2322ad570
3
+ size 80115210