lesso commited on
Commit
c21d58b
·
verified ·
1 Parent(s): a26bd9b

Удалены блоки <details>...</details> из README.md

Browse files
Files changed (1) hide show
  1. README.md +66 -153
README.md CHANGED
@@ -1,154 +1,67 @@
1
- ---
2
- library_name: peft
3
- base_model: katuni4ka/tiny-random-dbrx
4
- tags:
5
- - axolotl
6
- - generated_from_trainer
7
- model-index:
8
- - name: 487d0c43-02d9-420f-b509-b475f325c574
9
- results: []
10
- ---
11
-
12
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
- should probably proofread and complete it, then remove this comment. -->
14
-
15
- [<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)
16
- <details><summary>See axolotl config</summary>
17
-
18
- axolotl version: `0.4.1`
19
- ```yaml
20
- adapter: lora
21
- auto_find_batch_size: true
22
- base_model: katuni4ka/tiny-random-dbrx
23
- bf16: auto
24
- chat_template: llama3
25
- dataset_prepared_path: null
26
- datasets:
27
- - data_files:
28
- - 2aaaa7e6d073c458_train_data.json
29
- ds_type: json
30
- format: custom
31
- path: /workspace/input_data/2aaaa7e6d073c458_train_data.json
32
- type:
33
- field_input: original_code
34
- field_instruction: update_snippet
35
- field_output: final_code
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
- early_stopping_patience: 3
44
- eval_max_new_tokens: 128
45
- eval_steps: 50
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: false
53
- group_by_length: true
54
- hub_model_id: lesso/487d0c43-02d9-420f-b509-b475f325c574
55
- hub_repo: null
56
- hub_strategy: checkpoint
57
- hub_token: null
58
- learning_rate: 0.000217
59
- load_in_4bit: false
60
- load_in_8bit: false
61
- local_rank: null
62
- logging_steps: 50
63
- lora_alpha: 128
64
- lora_dropout: 0.05
65
- lora_fan_in_fan_out: null
66
- lora_model_dir: null
67
- lora_r: 64
68
- lora_target_linear: true
69
- lr_scheduler: constant
70
- max_grad_norm: 1.0
71
- max_steps: 400
72
- micro_batch_size: 32
73
- mlflow_experiment_name: /tmp/G.O.D/2aaaa7e6d073c458_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: null
81
- sample_packing: false
82
- save_steps: 50
83
- saves_per_epoch: null
84
- sequence_len: 512
85
- strict: false
86
- tf32: true
87
- tokenizer_type: AutoTokenizer
88
- train_on_inputs: false
89
- trust_remote_code: true
90
- val_set_size: 0.05
91
- wandb_entity: null
92
- wandb_mode: online
93
- wandb_name: dd61b94e-cb7f-4cdd-8af3-38cc544bb3b0
94
- wandb_project: 17a
95
- wandb_run: your_name
96
- wandb_runid: dd61b94e-cb7f-4cdd-8af3-38cc544bb3b0
97
- warmup_steps: 50
98
- weight_decay: 0.0
99
- xformers_attention: null
100
-
101
- ```
102
-
103
- </details><br>
104
-
105
- # 487d0c43-02d9-420f-b509-b475f325c574
106
-
107
- This model is a fine-tuned version of [katuni4ka/tiny-random-dbrx](https://huggingface.co/katuni4ka/tiny-random-dbrx) on the None dataset.
108
- It achieves the following results on the evaluation set:
109
- - Loss: 11.5
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: 0.000217
129
- - train_batch_size: 32
130
- - eval_batch_size: 32
131
- - seed: 42
132
- - gradient_accumulation_steps: 4
133
- - total_train_batch_size: 128
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: constant
136
- - lr_scheduler_warmup_steps: 50
137
- - training_steps: 127
138
-
139
- ### Training results
140
-
141
- | Training Loss | Epoch | Step | Validation Loss |
142
- |:-------------:|:------:|:----:|:---------------:|
143
- | No log | 0.0237 | 1 | 11.5 |
144
- | 46.0 | 1.1834 | 50 | 11.5 |
145
- | 46.0 | 2.3669 | 100 | 11.5 |
146
-
147
-
148
- ### Framework versions
149
-
150
- - PEFT 0.13.2
151
- - Transformers 4.46.0
152
- - Pytorch 2.5.0+cu124
153
- - Datasets 3.0.1
154
  - Tokenizers 0.20.1
 
1
+ ---
2
+ library_name: peft
3
+ base_model: katuni4ka/tiny-random-dbrx
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: 487d0c43-02d9-420f-b509-b475f325c574
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <br>
17
+
18
+ # 487d0c43-02d9-420f-b509-b475f325c574
19
+
20
+ This model is a fine-tuned version of [katuni4ka/tiny-random-dbrx](https://huggingface.co/katuni4ka/tiny-random-dbrx) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 11.5
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.000217
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 128
47
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: constant
49
+ - lr_scheduler_warmup_steps: 50
50
+ - training_steps: 127
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | No log | 0.0237 | 1 | 11.5 |
57
+ | 46.0 | 1.1834 | 50 | 11.5 |
58
+ | 46.0 | 2.3669 | 100 | 11.5 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.13.2
64
+ - Transformers 4.46.0
65
+ - Pytorch 2.5.0+cu124
66
+ - Datasets 3.0.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  - Tokenizers 0.20.1