Hugging Face's logo

Kromtao
/
7f55a22d-27c6-40c0-9242-7c3a5f04e3f6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
Kromtao commited on
Commit
9b68ec4
·
verified ·
1 Parent(s): 6ce1e60

End of training

Browse files
Files changed (2) hide show
  1. README.md +153 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/SmolLM2-135M
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 7f55a22d-27c6-40c0-9242-7c3a5f04e3f6
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/SmolLM2-135M
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 14efd411bd3f1df0_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/14efd411bd3f1df0_train_data.json
32
+ type:
33
+ field_input: input
34
+ field_instruction: instruct
35
+ field_output: output
36
+ format: '{instruction} {input}'
37
+ no_input_format: '{instruction}'
38
+ system_format: '{system}'
39
+ system_prompt: ''
40
+ debug: null
41
+ deepspeed: null
42
+ do_eval: true
43
+ eval_batch_size: 8
44
+ eval_max_new_tokens: 128
45
+ eval_steps: 2174
46
+ evals_per_epoch: null
47
+ flash_attention: true
48
+ fp16: false
49
+ fsdp: null
50
+ fsdp_config: null
51
+ gradient_accumulation_steps: 4
52
+ gradient_checkpointing: true
53
+ group_by_length: true
54
+ hub_model_id: Kromtao/7f55a22d-27c6-40c0-9242-7c3a5f04e3f6
55
+ hub_repo: null
56
+ hub_strategy: checkpoint
57
+ hub_token: null
58
+ learning_rate: 0.0002
59
+ local_rank: null
60
+ logging_steps: 50
61
+ lora_alpha: 16
62
+ lora_dropout: 0.1
63
+ lora_fan_in_fan_out: false
64
+ lora_model_dir: null
65
+ lora_r: 8
66
+ lora_target_linear: true
67
+ lr_scheduler: cosine
68
+ max_grad_norm: 1.0
69
+ max_steps: 4348
70
+ micro_batch_size: 8
71
+ mlflow_experiment_name: /tmp/14efd411bd3f1df0_train_data.json
72
+ model_type: AutoModelForCausalLM
73
+ num_epochs: 10
74
+ optimizer: adamw_torch_fused
75
+ output_dir: miner_id_24
76
+ pad_to_sequence_len: true
77
+ resume_from_checkpoint: null
78
+ s2_attention: false
79
+ sample_packing: false
80
+ save_steps: 2174
81
+ saves_per_epoch: null
82
+ seed: 9103
83
+ sequence_len: 1024
84
+ strict: false
85
+ tf32: true
86
+ tokenizer_type: AutoTokenizer
87
+ train_on_inputs: false
88
+ trust_remote_code: true
89
+ val_set_size: 0.05
90
+ wandb_entity: null
91
+ wandb_mode: online
92
+ wandb_name: 05a93f74-543d-453e-bebf-b28930df5cdc
93
+ wandb_project: kr03
94
+ wandb_run: your_name
95
+ wandb_runid: 05a93f74-543d-453e-bebf-b28930df5cdc
96
+ warmup_steps: 100
97
+ weight_decay: 0.01
98
+ xformers_attention: true
99
+
100
+ ```
101
+
102
+ </details><br>
103
+
104
+ # 7f55a22d-27c6-40c0-9242-7c3a5f04e3f6
105
+
106
+ This model is a fine-tuned version of [unsloth/SmolLM2-135M](https://huggingface.co/unsloth/SmolLM2-135M) on the None dataset.
107
+ It achieves the following results on the evaluation set:
108
+ - Loss: 1.7674
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: 0.0002
128
+ - train_batch_size: 8
129
+ - eval_batch_size: 8
130
+ - seed: 9103
131
+ - gradient_accumulation_steps: 4
132
+ - total_train_batch_size: 32
133
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
136
+ - training_steps: 4348
137
+
138
+ ### Training results
139
+
140
+ | Training Loss | Epoch | Step | Validation Loss |
141
+ |:-------------:|:------:|:----:|:---------------:|
142
+ | No log | 0.0001 | 1 | 2.4202 |
143
+ | 1.7645 | 0.2442 | 2174 | 1.7905 |
144
+ | 1.8049 | 0.4884 | 4348 | 1.7674 |
145
+
146
+
147
+ ### Framework versions
148
+
149
+ - PEFT 0.13.2
150
+ - Transformers 4.46.0
151
+ - Pytorch 2.5.0+cu124
152
+ - Datasets 3.0.1
153
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e302d224e99e362e76267713f0830bc96f023c25be1dbf764fd13e1f1ba2b475
3
+ size 9919898