ardaspear commited on
Commit
fb21fd1
·
verified ·
1 Parent(s): 26a35c3

End of training

Browse files
Files changed (2) hide show
  1. README.md +163 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 8a7b1c44-45ee-44f3-934d-ddc8b6e082f1
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
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 55309917cf7570e3_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/55309917cf7570e3_train_data.json
32
+ type:
33
+ field_instruction: problem
34
+ field_output: solution
35
+ format: '{instruction}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ deepspeed: null
41
+ early_stopping_patience: null
42
+ eval_max_new_tokens: 128
43
+ eval_table_size: null
44
+ evals_per_epoch: 4
45
+ flash_attention: false
46
+ fp16: true
47
+ fsdp: null
48
+ fsdp_config: null
49
+ gradient_accumulation_steps: 4
50
+ gradient_checkpointing: true
51
+ gradient_clipping: 1.0
52
+ group_by_length: false
53
+ hub_model_id: ardaspear/8a7b1c44-45ee-44f3-934d-ddc8b6e082f1
54
+ hub_repo: null
55
+ hub_strategy: checkpoint
56
+ hub_token: null
57
+ learning_rate: 0.0001
58
+ load_in_4bit: false
59
+ load_in_8bit: false
60
+ local_rank: 0
61
+ logging_steps: 3
62
+ lora_alpha: 128
63
+ lora_dropout: 0.1
64
+ lora_fan_in_fan_out: true
65
+ lora_model_dir: null
66
+ lora_r: 64
67
+ lora_target_linear: true
68
+ lr_scheduler: cosine
69
+ max_grad_norm: 1.0
70
+ max_memory:
71
+ 0: 72GB
72
+ max_steps: 100
73
+ micro_batch_size: 4
74
+ mlflow_experiment_name: /tmp/55309917cf7570e3_train_data.json
75
+ model_type: AutoModelForCausalLM
76
+ num_epochs: 3
77
+ optimizer: adamw_bnb_8bit
78
+ output_dir: miner_id_24
79
+ pad_to_sequence_len: true
80
+ resume_from_checkpoint: null
81
+ s2_attention: false
82
+ sample_packing: false
83
+ saves_per_epoch: 4
84
+ sequence_len: 1024
85
+ strict: false
86
+ tf32: false
87
+ tokenizer_type: AutoTokenizer
88
+ train_on_inputs: false
89
+ trust_remote_code: true
90
+ val_set_size: 0.05
91
+ wandb_entity: leixa-personal
92
+ wandb_mode: online
93
+ wandb_name: 8a7b1c44-45ee-44f3-934d-ddc8b6e082f1
94
+ wandb_project: Gradients-On-Two
95
+ wandb_run: your_name
96
+ wandb_runid: 8a7b1c44-45ee-44f3-934d-ddc8b6e082f1
97
+ warmup_steps: 10
98
+ weight_decay: 0.01
99
+ xformers_attention: null
100
+
101
+ ```
102
+
103
+ </details><br>
104
+
105
+ # 8a7b1c44-45ee-44f3-934d-ddc8b6e082f1
106
+
107
+ This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the None dataset.
108
+ It achieves the following results on the evaluation set:
109
+ - Loss: nan
110
+
111
+ ## Model description
112
+
113
+ More information needed
114
+
115
+ ## Intended uses & limitations
116
+
117
+ More information needed
118
+
119
+ ## Training and evaluation data
120
+
121
+ More information needed
122
+
123
+ ## Training procedure
124
+
125
+ ### Training hyperparameters
126
+
127
+ The following hyperparameters were used during training:
128
+ - learning_rate: 0.0001
129
+ - train_batch_size: 4
130
+ - eval_batch_size: 4
131
+ - seed: 42
132
+ - gradient_accumulation_steps: 4
133
+ - total_train_batch_size: 16
134
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
135
+ - lr_scheduler_type: cosine
136
+ - lr_scheduler_warmup_steps: 10
137
+ - training_steps: 100
138
+
139
+ ### Training results
140
+
141
+ | Training Loss | Epoch | Step | Validation Loss |
142
+ |:-------------:|:------:|:----:|:---------------:|
143
+ | No log | 0.0062 | 1 | nan |
144
+ | 0.0 | 0.0555 | 9 | nan |
145
+ | 0.0 | 0.1109 | 18 | nan |
146
+ | 0.0 | 0.1664 | 27 | nan |
147
+ | 0.0 | 0.2219 | 36 | nan |
148
+ | 0.0 | 0.2773 | 45 | nan |
149
+ | 0.0 | 0.3328 | 54 | nan |
150
+ | 0.0 | 0.3883 | 63 | nan |
151
+ | 0.0 | 0.4438 | 72 | nan |
152
+ | 0.0 | 0.4992 | 81 | nan |
153
+ | 0.0 | 0.5547 | 90 | nan |
154
+ | 0.0 | 0.6102 | 99 | nan |
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
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4739e7fcb68b61ff8c392994734b03cb39c86c0b7ee5cb565316e3391f94033
3
+ size 140892234