DeepDream2045 commited on
Commit
67ff1e3
1 Parent(s): 5c89d4e

End of training

Browse files
Files changed (2) hide show
  1. README.md +155 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: NousResearch/CodeLlama-7b-hf-flash
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: 83ca31f7-3c73-4504-8201-3ccdbdd0ed76
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/CodeLlama-7b-hf-flash
22
+ bf16: auto
23
+ chat_template: llama3
24
+ dataset_prepared_path: null
25
+ datasets:
26
+ - data_files:
27
+ - 7a7b16003e342160_train_data.json
28
+ ds_type: json
29
+ format: custom
30
+ path: /workspace/input_data/7a7b16003e342160_train_data.json
31
+ type:
32
+ field_input: code
33
+ field_instruction: text
34
+ field_output: language
35
+ format: '{instruction} {input}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ deepspeed: null
41
+ early_stopping_patience: 1
42
+ eval_max_new_tokens: 128
43
+ eval_steps: 25
44
+ eval_table_size: null
45
+ flash_attention: false
46
+ fp16: false
47
+ fsdp: null
48
+ fsdp_config: null
49
+ gradient_accumulation_steps: 16
50
+ gradient_checkpointing: true
51
+ group_by_length: true
52
+ hub_model_id: DeepDream2045/83ca31f7-3c73-4504-8201-3ccdbdd0ed76
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: false
59
+ local_rank: null
60
+ logging_steps: 1
61
+ lora_alpha: 64
62
+ lora_dropout: 0.05
63
+ lora_fan_in_fan_out: null
64
+ lora_model_dir: null
65
+ lora_r: 32
66
+ lora_target_linear: true
67
+ lr_scheduler: cosine
68
+ max_steps: 50
69
+ micro_batch_size: 2
70
+ mlflow_experiment_name: /tmp/7a7b16003e342160_train_data.json
71
+ model_type: AutoModelForCausalLM
72
+ num_epochs: 3
73
+ optimizer: adamw_torch
74
+ output_dir: miner_id_24
75
+ pad_to_sequence_len: true
76
+ resume_from_checkpoint: null
77
+ s2_attention: null
78
+ sample_packing: false
79
+ save_steps: 25
80
+ sequence_len: 2048
81
+ special_tokens:
82
+ pad_token: </s>
83
+ strict: false
84
+ tf32: false
85
+ tokenizer_type: AutoTokenizer
86
+ train_on_inputs: false
87
+ trust_remote_code: true
88
+ val_set_size: 0.05
89
+ wandb_entity: null
90
+ wandb_mode: online
91
+ wandb_name: 83ca31f7-3c73-4504-8201-3ccdbdd0ed76
92
+ wandb_project: Gradients-On-Demand
93
+ wandb_run: your_name
94
+ wandb_runid: 83ca31f7-3c73-4504-8201-3ccdbdd0ed76
95
+ warmup_ratio: 0.05
96
+ weight_decay: 0.01
97
+ xformers_attention: true
98
+
99
+ ```
100
+
101
+ </details><br>
102
+
103
+ # 83ca31f7-3c73-4504-8201-3ccdbdd0ed76
104
+
105
+ This model is a fine-tuned version of [NousResearch/CodeLlama-7b-hf-flash](https://huggingface.co/NousResearch/CodeLlama-7b-hf-flash) on the None dataset.
106
+ It achieves the following results on the evaluation set:
107
+ - Loss: 0.0016
108
+
109
+ ## Model description
110
+
111
+ More information needed
112
+
113
+ ## Intended uses & limitations
114
+
115
+ More information needed
116
+
117
+ ## Training and evaluation data
118
+
119
+ More information needed
120
+
121
+ ## Training procedure
122
+
123
+ ### Training hyperparameters
124
+
125
+ The following hyperparameters were used during training:
126
+ - learning_rate: 0.0001
127
+ - train_batch_size: 2
128
+ - eval_batch_size: 2
129
+ - seed: 42
130
+ - distributed_type: multi-GPU
131
+ - num_devices: 4
132
+ - gradient_accumulation_steps: 16
133
+ - total_train_batch_size: 128
134
+ - total_eval_batch_size: 8
135
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
136
+ - lr_scheduler_type: cosine
137
+ - lr_scheduler_warmup_steps: 2
138
+ - training_steps: 50
139
+
140
+ ### Training results
141
+
142
+ | Training Loss | Epoch | Step | Validation Loss |
143
+ |:-------------:|:------:|:----:|:---------------:|
144
+ | 114.627 | 0.0025 | 1 | 7.0684 |
145
+ | 0.0013 | 0.0636 | 25 | 0.0022 |
146
+ | 1.0866 | 0.1273 | 50 | 0.0016 |
147
+
148
+
149
+ ### Framework versions
150
+
151
+ - PEFT 0.13.2
152
+ - Transformers 4.46.0
153
+ - Pytorch 2.5.0+cu124
154
+ - Datasets 3.0.1
155
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ba796113ba8919c92161f291b5e4b7e3e825511ebb89eb755a600be0595a83
3
+ size 319977674