kooff11 commited on
Commit
4dd99a9
1 Parent(s): 08a607f

End of training

Browse files
Files changed (2) hide show
  1. README.md +162 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: oopsung/llama2-7b-n-ox-test-v1
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: 39680fe4-9a82-4294-926f-8d48aca8d8b3
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: oopsung/llama2-7b-n-ox-test-v1
22
+ bf16: auto
23
+ chat_template: llama3
24
+ dataset_prepared_path: null
25
+ datasets:
26
+ - data_files:
27
+ - 077f6099e46d64dd_train_data.json
28
+ ds_type: json
29
+ format: custom
30
+ path: /workspace/input_data/077f6099e46d64dd_train_data.json
31
+ type:
32
+ field_input: question
33
+ field_instruction: system_prompt
34
+ field_output: response
35
+ format: '{instruction} {input}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ deepspeed: null
41
+ device_map: auto
42
+ early_stopping_patience: null
43
+ eval_max_new_tokens: 128
44
+ eval_table_size: null
45
+ evals_per_epoch: 4
46
+ flash_attention: true
47
+ fp16: null
48
+ fsdp: null
49
+ fsdp_config: null
50
+ gradient_accumulation_steps: 32
51
+ gradient_checkpointing: false
52
+ group_by_length: false
53
+ hub_model_id: kooff11/39680fe4-9a82-4294-926f-8d48aca8d8b3
54
+ hub_repo: null
55
+ hub_strategy: checkpoint
56
+ hub_token: null
57
+ learning_rate: 0.0001
58
+ local_rank: null
59
+ logging_steps: 1
60
+ lora_alpha: 32
61
+ lora_dropout: 0.05
62
+ lora_fan_in_fan_out: null
63
+ lora_model_dir: null
64
+ lora_r: 16
65
+ lora_target_linear: true
66
+ lora_target_modules:
67
+ - q_proj
68
+ - v_proj
69
+ lr_scheduler: cosine
70
+ max_memory:
71
+ 0: 130GiB
72
+ 1: 130GiB
73
+ max_steps: 50
74
+ micro_batch_size: 2
75
+ mlflow_experiment_name: /tmp/077f6099e46d64dd_train_data.json
76
+ model_type: AutoModelForCausalLM
77
+ num_epochs: 1
78
+ optimizer: adamw_bnb_8bit
79
+ output_dir: miner_id_24
80
+ pad_to_sequence_len: true
81
+ quantization_config:
82
+ llm_int8_enable_fp32_cpu_offload: false
83
+ load_in_8bit: true
84
+ resume_from_checkpoint: null
85
+ s2_attention: null
86
+ sample_packing: false
87
+ saves_per_epoch: 4
88
+ sequence_len: 4056
89
+ strict: false
90
+ tf32: false
91
+ tokenizer_type: AutoTokenizer
92
+ train_on_inputs: false
93
+ trust_remote_code: true
94
+ val_set_size: 0.05
95
+ wandb_entity: null
96
+ wandb_mode: online
97
+ wandb_name: 39680fe4-9a82-4294-926f-8d48aca8d8b3
98
+ wandb_project: Gradients-On-Demand
99
+ wandb_run: your_name
100
+ wandb_runid: 39680fe4-9a82-4294-926f-8d48aca8d8b3
101
+ warmup_steps: 2
102
+ weight_decay: 0.0
103
+ xformers_attention: null
104
+
105
+ ```
106
+
107
+ </details><br>
108
+
109
+ # 39680fe4-9a82-4294-926f-8d48aca8d8b3
110
+
111
+ This model is a fine-tuned version of [oopsung/llama2-7b-n-ox-test-v1](https://huggingface.co/oopsung/llama2-7b-n-ox-test-v1) on the None dataset.
112
+ It achieves the following results on the evaluation set:
113
+ - Loss: 0.7736
114
+
115
+ ## Model description
116
+
117
+ More information needed
118
+
119
+ ## Intended uses & limitations
120
+
121
+ More information needed
122
+
123
+ ## Training and evaluation data
124
+
125
+ More information needed
126
+
127
+ ## Training procedure
128
+
129
+ ### Training hyperparameters
130
+
131
+ The following hyperparameters were used during training:
132
+ - learning_rate: 0.0001
133
+ - train_batch_size: 2
134
+ - eval_batch_size: 2
135
+ - seed: 42
136
+ - distributed_type: multi-GPU
137
+ - num_devices: 2
138
+ - gradient_accumulation_steps: 32
139
+ - total_train_batch_size: 128
140
+ - total_eval_batch_size: 4
141
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
142
+ - lr_scheduler_type: cosine
143
+ - lr_scheduler_warmup_steps: 2
144
+ - training_steps: 50
145
+
146
+ ### Training results
147
+
148
+ | Training Loss | Epoch | Step | Validation Loss |
149
+ |:-------------:|:------:|:----:|:---------------:|
150
+ | 1.3066 | 0.0141 | 1 | 1.3235 |
151
+ | 0.8649 | 0.1829 | 13 | 0.8647 |
152
+ | 0.8016 | 0.3657 | 26 | 0.7906 |
153
+ | 0.8068 | 0.5486 | 39 | 0.7736 |
154
+
155
+
156
+ ### Framework versions
157
+
158
+ - PEFT 0.13.2
159
+ - Transformers 4.46.0
160
+ - Pytorch 2.5.0+cu124
161
+ - Datasets 3.0.1
162
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b20323435eadeb000ebccc03af4da73140574ddc3a550f12aa8af86cce9d030
3
+ size 160069834