dada22231 commited on
Commit
9165b11
1 Parent(s): 07f16a0

End of training

Browse files
Files changed (2) hide show
  1. README.md +173 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/Qwen2-0.5B
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 8d04d9ea-e0f3-4c6e-961f-a0a74f997d39
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/Qwen2-0.5B
23
+ bf16: auto
24
+ chat_template: llama3
25
+ cosine_min_lr_ratio: 0.1
26
+ data_processes: 16
27
+ dataset_prepared_path: null
28
+ datasets:
29
+ - data_files:
30
+ - 26d967aab83e354b_train_data.json
31
+ ds_type: json
32
+ format: custom
33
+ path: /workspace/input_data/26d967aab83e354b_train_data.json
34
+ type:
35
+ field_input: id
36
+ field_instruction: consequence
37
+ field_output: clin_sig
38
+ format: '{instruction} {input}'
39
+ no_input_format: '{instruction}'
40
+ system_format: '{system}'
41
+ system_prompt: ''
42
+ debug: null
43
+ deepspeed: null
44
+ device_map: auto
45
+ do_eval: true
46
+ eval_batch_size: 1
47
+ eval_sample_packing: false
48
+ eval_steps: 25
49
+ evaluation_strategy: steps
50
+ flash_attention: false
51
+ fp16: null
52
+ fsdp: null
53
+ fsdp_config: null
54
+ gradient_accumulation_steps: 32
55
+ gradient_checkpointing: true
56
+ group_by_length: true
57
+ hub_model_id: dada22231/8d04d9ea-e0f3-4c6e-961f-a0a74f997d39
58
+ hub_strategy: checkpoint
59
+ hub_token: null
60
+ hub_username: dada22231
61
+ learning_rate: 0.0001
62
+ load_in_4bit: false
63
+ load_in_8bit: false
64
+ local_rank: null
65
+ logging_steps: 1
66
+ lora_alpha: 64
67
+ lora_dropout: 0.05
68
+ lora_fan_in_fan_out: null
69
+ lora_model_dir: null
70
+ lora_r: 32
71
+ lora_target_linear: true
72
+ lora_target_modules:
73
+ - q_proj
74
+ - v_proj
75
+ lr_scheduler: cosine
76
+ max_grad_norm: 1.0
77
+ max_memory:
78
+ 0: 70GiB
79
+ 1: 70GiB
80
+ 2: 70GiB
81
+ 3: 70GiB
82
+ max_steps: 50
83
+ micro_batch_size: 1
84
+ mlflow_experiment_name: /tmp/26d967aab83e354b_train_data.json
85
+ model_type: AutoModelForCausalLM
86
+ num_epochs: 3
87
+ optim_args:
88
+ adam_beta1: 0.9
89
+ adam_beta2: 0.95
90
+ adam_epsilon: 1e-5
91
+ optimizer: adamw_torch
92
+ output_dir: miner_id_24
93
+ pad_to_sequence_len: true
94
+ repository_id: dada22231/8d04d9ea-e0f3-4c6e-961f-a0a74f997d39
95
+ resume_from_checkpoint: null
96
+ s2_attention: null
97
+ sample_packing: false
98
+ save_steps: 25
99
+ save_strategy: steps
100
+ sequence_len: 2048
101
+ strict: false
102
+ tf32: false
103
+ tokenizer_type: AutoTokenizer
104
+ torch_compile: false
105
+ train_on_inputs: false
106
+ trust_remote_code: true
107
+ val_set_size: 50
108
+ wandb_entity: null
109
+ wandb_mode: online
110
+ wandb_name: 8d04d9ea-e0f3-4c6e-961f-a0a74f997d39
111
+ wandb_project: Public_TuningSN
112
+ wandb_runid: 8d04d9ea-e0f3-4c6e-961f-a0a74f997d39
113
+ warmup_ratio: 0.04
114
+ weight_decay: 0.01
115
+ xformers_attention: null
116
+
117
+ ```
118
+
119
+ </details><br>
120
+
121
+ # 8d04d9ea-e0f3-4c6e-961f-a0a74f997d39
122
+
123
+ This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the None dataset.
124
+ It achieves the following results on the evaluation set:
125
+ - Loss: nan
126
+
127
+ ## Model description
128
+
129
+ More information needed
130
+
131
+ ## Intended uses & limitations
132
+
133
+ More information needed
134
+
135
+ ## Training and evaluation data
136
+
137
+ More information needed
138
+
139
+ ## Training procedure
140
+
141
+ ### Training hyperparameters
142
+
143
+ The following hyperparameters were used during training:
144
+ - learning_rate: 0.0001
145
+ - train_batch_size: 1
146
+ - eval_batch_size: 1
147
+ - seed: 42
148
+ - distributed_type: multi-GPU
149
+ - num_devices: 4
150
+ - gradient_accumulation_steps: 32
151
+ - total_train_batch_size: 128
152
+ - total_eval_batch_size: 4
153
+ - optimizer: Use OptimizerNames.ADAMW_TORCH 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
154
+ - lr_scheduler_type: cosine
155
+ - lr_scheduler_warmup_steps: 2
156
+ - training_steps: 50
157
+
158
+ ### Training results
159
+
160
+ | Training Loss | Epoch | Step | Validation Loss |
161
+ |:-------------:|:------:|:----:|:---------------:|
162
+ | 0.0 | 0.0006 | 1 | nan |
163
+ | 0.0 | 0.0145 | 25 | nan |
164
+ | 0.0 | 0.0289 | 50 | nan |
165
+
166
+
167
+ ### Framework versions
168
+
169
+ - PEFT 0.13.2
170
+ - Transformers 4.46.0
171
+ - Pytorch 2.5.0+cu124
172
+ - Datasets 3.0.1
173
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c69aa30f682bfc3ea2b882fa6d573f81d84d2f8ab505609bcba03d5387b22421
3
+ size 70506570