Hugging Face's logo

Alphatao
/
37fb3c3c-0d51-45cc-88ad-367b16fb033e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
Alphatao commited on
Commit
a774ea7
·
verified ·
1 Parent(s): 7c2d4e0

End of training

Browse files
Files changed (3) hide show
  1. README.md +164 -0
  2. adapter_model.bin +3 -0
  3. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/tinyllama
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 37fb3c3c-0d51-45cc-88ad-367b16fb033e
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/tinyllama
23
+ bf16: true
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - ef34dd30995e74ec_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/ef34dd30995e74ec_train_data.json
32
+ type:
33
+ field_input: decomposition
34
+ field_instruction: question_text
35
+ field_output: operators
36
+ format: '{instruction} {input}'
37
+ no_input_format: '{instruction}'
38
+ system_format: '{system}'
39
+ system_prompt: ''
40
+ debug: null
41
+ device_map:
42
+ ? ''
43
+ : 0,1,2,3,4,5,6,7
44
+ early_stopping_patience: 2
45
+ eval_max_new_tokens: 128
46
+ eval_steps: 100
47
+ eval_table_size: null
48
+ flash_attention: true
49
+ gradient_accumulation_steps: 8
50
+ gradient_checkpointing: true
51
+ group_by_length: false
52
+ hub_model_id: Alphatao/37fb3c3c-0d51-45cc-88ad-367b16fb033e
53
+ hub_repo: null
54
+ hub_strategy: null
55
+ hub_token: null
56
+ learning_rate: 0.0002
57
+ load_best_model_at_end: true
58
+ load_in_4bit: false
59
+ load_in_8bit: false
60
+ local_rank: null
61
+ logging_steps: 1
62
+ lora_alpha: 32
63
+ lora_dropout: 0.05
64
+ lora_fan_in_fan_out: null
65
+ lora_model_dir: null
66
+ lora_r: 16
67
+ lora_target_linear: true
68
+ lora_target_modules:
69
+ - q_proj
70
+ - k_proj
71
+ - v_proj
72
+ - o_proj
73
+ - down_proj
74
+ - up_proj
75
+ lr_scheduler: cosine
76
+ max_grad_norm: 1.0
77
+ max_steps: 4140
78
+ micro_batch_size: 4
79
+ mlflow_experiment_name: /tmp/ef34dd30995e74ec_train_data.json
80
+ model_type: AutoModelForCausalLM
81
+ num_epochs: 2
82
+ optimizer: adamw_bnb_8bit
83
+ output_dir: miner_id_24
84
+ pad_to_sequence_len: true
85
+ resume_from_checkpoint: null
86
+ s2_attention: null
87
+ sample_packing: false
88
+ save_steps: 100
89
+ sequence_len: 2048
90
+ strict: false
91
+ tf32: true
92
+ tokenizer_type: AutoTokenizer
93
+ train_on_inputs: false
94
+ trust_remote_code: true
95
+ val_set_size: 0.04
96
+ wandb_entity: null
97
+ wandb_mode: online
98
+ wandb_name: 111c6782-09b2-48b1-8a6e-cb4b734bc85e
99
+ wandb_project: Gradients-On-Demand
100
+ wandb_run: your_name
101
+ wandb_runid: 111c6782-09b2-48b1-8a6e-cb4b734bc85e
102
+ warmup_steps: 10
103
+ weight_decay: 0.0
104
+ xformers_attention: null
105
+
106
+ ```
107
+
108
+ </details><br>
109
+
110
+ # 37fb3c3c-0d51-45cc-88ad-367b16fb033e
111
+
112
+ This model is a fine-tuned version of [unsloth/tinyllama](https://huggingface.co/unsloth/tinyllama) on the None dataset.
113
+ It achieves the following results on the evaluation set:
114
+ - Loss: 0.0349
115
+
116
+ ## Model description
117
+
118
+ More information needed
119
+
120
+ ## Intended uses & limitations
121
+
122
+ More information needed
123
+
124
+ ## Training and evaluation data
125
+
126
+ More information needed
127
+
128
+ ## Training procedure
129
+
130
+ ### Training hyperparameters
131
+
132
+ The following hyperparameters were used during training:
133
+ - learning_rate: 0.0002
134
+ - train_batch_size: 4
135
+ - eval_batch_size: 4
136
+ - seed: 42
137
+ - gradient_accumulation_steps: 8
138
+ - total_train_batch_size: 32
139
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
140
+ - lr_scheduler_type: cosine
141
+ - lr_scheduler_warmup_steps: 10
142
+ - training_steps: 3561
143
+
144
+ ### Training results
145
+
146
+ | Training Loss | Epoch | Step | Validation Loss |
147
+ |:-------------:|:------:|:----:|:---------------:|
148
+ | 5.7121 | 0.0006 | 1 | 5.4100 |
149
+ | 0.0105 | 0.0562 | 100 | 0.0410 |
150
+ | 0.0822 | 0.1123 | 200 | 0.0213 |
151
+ | 0.0096 | 0.1685 | 300 | 0.0116 |
152
+ | 0.0006 | 0.2247 | 400 | 0.0067 |
153
+ | 0.0178 | 0.2808 | 500 | 0.0044 |
154
+ | 0.0051 | 0.3370 | 600 | 0.0527 |
155
+ | 0.0326 | 0.3931 | 700 | 0.0349 |
156
+
157
+
158
+ ### Framework versions
159
+
160
+ - PEFT 0.13.2
161
+ - Transformers 4.46.0
162
+ - Pytorch 2.5.0+cu124
163
+ - Datasets 3.0.1
164
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25410cf2f9c52d2b4b39e76e7e5b5ca22b03ae1987321f396fa2534a84211b55
3
+ size 50573530
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:546f37f88e2b113b53b964fe7abe854b90106c7cbf6b757492dff264e53c9c71
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ee6bbbd04419f42f1871110fa72a50868a097902691a44940c23e8d6751fbf
3
  size 50503544