leixa commited on
Commit
68c6045
1 Parent(s): 06c272c

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
+ license: apache-2.0
4
+ base_model: unsloth/Qwen2.5-Math-7B-Instruct
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: c0e58293-8a21-4bda-a95f-61e0bc9cc9e3
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/Qwen2.5-Math-7B-Instruct
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - d50b59888f520c0e_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/d50b59888f520c0e_train_data.json
32
+ type:
33
+ field_input: Resume_str
34
+ field_instruction: Category
35
+ field_output: Resume_html
36
+ format: '{instruction} {input}'
37
+ no_input_format: '{instruction}'
38
+ system_format: '{system}'
39
+ system_prompt: ''
40
+ debug: null
41
+ deepspeed: null
42
+ early_stopping_patience: null
43
+ eval_max_new_tokens: 128
44
+ eval_table_size: null
45
+ evals_per_epoch: 4
46
+ flash_attention: false
47
+ fp16: true
48
+ fsdp: null
49
+ fsdp_config: null
50
+ gradient_accumulation_steps: 4
51
+ gradient_checkpointing: true
52
+ group_by_length: false
53
+ hub_model_id: leixa/c0e58293-8a21-4bda-a95f-61e0bc9cc9e3
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_memory:
70
+ 0: 72GB
71
+ max_steps: 100
72
+ micro_batch_size: 8
73
+ mlflow_experiment_name: /tmp/d50b59888f520c0e_train_data.json
74
+ model_type: AutoModelForCausalLM
75
+ num_epochs: 3
76
+ optimizer: adamw_bnb_8bit
77
+ output_dir: miner_id_24
78
+ pad_to_sequence_len: true
79
+ resume_from_checkpoint: null
80
+ s2_attention: false
81
+ sample_packing: false
82
+ saves_per_epoch: 4
83
+ sequence_len: 1024
84
+ strict: false
85
+ tf32: false
86
+ tokenizer_type: AutoTokenizer
87
+ train_on_inputs: false
88
+ trust_remote_code: true
89
+ val_set_size: 0.05
90
+ wandb_entity: leixa-personal
91
+ wandb_mode: online
92
+ wandb_name: c0e58293-8a21-4bda-a95f-61e0bc9cc9e3
93
+ wandb_project: Gradients-On-Demand
94
+ wandb_run: your_name
95
+ wandb_runid: c0e58293-8a21-4bda-a95f-61e0bc9cc9e3
96
+ warmup_steps: 10
97
+ weight_decay: 0.01
98
+ xformers_attention: null
99
+
100
+ ```
101
+
102
+ </details><br>
103
+
104
+ # c0e58293-8a21-4bda-a95f-61e0bc9cc9e3
105
+
106
+ This model is a fine-tuned version of [unsloth/Qwen2.5-Math-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Math-7B-Instruct) on the None dataset.
107
+ It achieves the following results on the evaluation set:
108
+ - Loss: nan
109
+
110
+ ## Model description
111
+
112
+ More information needed
113
+
114
+ ## Intended uses & limitations
115
+
116
+ More information needed
117
+
118
+ ## Training and evaluation data
119
+
120
+ More information needed
121
+
122
+ ## Training procedure
123
+
124
+ ### Training hyperparameters
125
+
126
+ The following hyperparameters were used during training:
127
+ - learning_rate: 0.0001
128
+ - train_batch_size: 8
129
+ - eval_batch_size: 8
130
+ - seed: 42
131
+ - gradient_accumulation_steps: 4
132
+ - total_train_batch_size: 32
133
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
134
+ - lr_scheduler_type: cosine
135
+ - lr_scheduler_warmup_steps: 10
136
+ - training_steps: 100
137
+
138
+ ### Training results
139
+
140
+ | Training Loss | Epoch | Step | Validation Loss |
141
+ |:-------------:|:------:|:----:|:---------------:|
142
+ | No log | 0.0147 | 1 | nan |
143
+ | 13.2201 | 0.1324 | 9 | nan |
144
+ | 3.6238 | 0.2647 | 18 | nan |
145
+ | 15.9645 | 0.3971 | 27 | nan |
146
+ | 1.5029 | 0.5294 | 36 | nan |
147
+ | 10.799 | 0.6618 | 45 | nan |
148
+ | 16.1705 | 0.7941 | 54 | nan |
149
+ | 8.2233 | 0.9265 | 63 | nan |
150
+ | 17.1026 | 1.0588 | 72 | nan |
151
+ | 9.0086 | 1.1912 | 81 | nan |
152
+ | 8.1206 | 1.3235 | 90 | nan |
153
+ | 2.4601 | 1.4559 | 99 | nan |
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 sha256:970bba8fd2b1d58f3d7947d072bbce381f8432244eea3f5c34cf8555696015a4
3
+ size 646064426