Files changed (1) hide show
  1. README.md +170 -156
README.md CHANGED
@@ -1,157 +1,171 @@
1
- ---
2
- library_name: peft
3
- license: apache-2.0
4
- base_model: Qwen/Qwen2.5-1.5B
5
- tags:
6
- - axolotl
7
- - generated_from_trainer
8
- model-index:
9
- - name: 8a88bad2-f185-4581-848c-17a0164a60b7
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: Qwen/Qwen2.5-1.5B
23
- bf16: auto
24
- chat_template: llama3
25
- dataset_prepared_path: null
26
- datasets:
27
- - data_files:
28
- - 17fc88a2b34e0b71_train_data.json
29
- ds_type: json
30
- format: custom
31
- path: /workspace/input_data/17fc88a2b34e0b71_train_data.json
32
- type:
33
- field_input: repo_name
34
- field_instruction: path
35
- field_output: content
36
- format: '{instruction} {input}'
37
- no_input_format: '{instruction}'
38
- system_format: '{system}'
39
- system_prompt: ''
40
- debug: null
41
- deepspeed: null
42
- device: cuda
43
- early_stopping_patience: 1
44
- eval_max_new_tokens: 128
45
- eval_steps: 5
46
- eval_table_size: null
47
- evals_per_epoch: null
48
- flash_attention: false
49
- fp16: null
50
- gradient_accumulation_steps: 4
51
- gradient_checkpointing: true
52
- group_by_length: false
53
- hub_model_id: joboffer/8a88bad2-f185-4581-848c-17a0164a60b7
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: null
61
- logging_steps: 3
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
- lr_scheduler: cosine
69
- max_memory:
70
- 0: 80GiB
71
- max_steps: 30
72
- micro_batch_size: 2
73
- mlflow_experiment_name: /tmp/17fc88a2b34e0b71_train_data.json
74
- model_type: AutoModelForCausalLM
75
- num_epochs: 1
76
- optimizer: adamw_torch
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: 10
83
- sequence_len: 2048
84
- strict: false
85
- tf32: false
86
- tokenizer_type: AutoTokenizer
87
- train_on_inputs: true
88
- trust_remote_code: true
89
- val_set_size: 0.05
90
- wandb_entity: null
91
- wandb_mode: online
92
- wandb_name: 23ada34b-aa21-426c-83a9-14a74929231e
93
- wandb_project: Gradients-On-Demand
94
- wandb_run: your_name
95
- wandb_runid: 23ada34b-aa21-426c-83a9-14a74929231e
96
- warmup_steps: 5
97
- weight_decay: 0.01
98
- xformers_attention: true
99
-
100
- ```
101
-
102
- </details><br>
103
-
104
- # 8a88bad2-f185-4581-848c-17a0164a60b7
105
-
106
- This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset.
107
- It achieves the following results on the evaluation set:
108
- - Loss: 1.0507
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: 2
129
- - eval_batch_size: 2
130
- - seed: 42
131
- - gradient_accumulation_steps: 4
132
- - total_train_batch_size: 8
133
- - optimizer: Use OptimizerNames.ADAMW_TORCH 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: 5
136
- - training_steps: 30
137
-
138
- ### Training results
139
-
140
- | Training Loss | Epoch | Step | Validation Loss |
141
- |:-------------:|:------:|:----:|:---------------:|
142
- | No log | 0.0027 | 1 | 1.0707 |
143
- | 1.0383 | 0.0135 | 5 | 1.0691 |
144
- | 1.032 | 0.0270 | 10 | 1.0626 |
145
- | 1.1076 | 0.0405 | 15 | 1.0567 |
146
- | 1.0528 | 0.0539 | 20 | 1.0528 |
147
- | 0.9893 | 0.0674 | 25 | 1.0510 |
148
- | 1.0197 | 0.0809 | 30 | 1.0507 |
149
-
150
-
151
- ### Framework versions
152
-
153
- - PEFT 0.13.2
154
- - Transformers 4.46.0
155
- - Pytorch 2.5.0+cu124
156
- - Datasets 3.0.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
157
  - Tokenizers 0.20.1
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2.5-1.5B
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ language:
9
+ - zho
10
+ - eng
11
+ - fra
12
+ - spa
13
+ - por
14
+ - deu
15
+ - ita
16
+ - rus
17
+ - jpn
18
+ - kor
19
+ - vie
20
+ - tha
21
+ - ara
22
+ model-index:
23
+ - name: 8a88bad2-f185-4581-848c-17a0164a60b7
24
+ results: []
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ [<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)
31
+ <details><summary>See axolotl config</summary>
32
+
33
+ axolotl version: `0.4.1`
34
+ ```yaml
35
+ adapter: lora
36
+ base_model: Qwen/Qwen2.5-1.5B
37
+ bf16: auto
38
+ chat_template: llama3
39
+ dataset_prepared_path: null
40
+ datasets:
41
+ - data_files:
42
+ - 17fc88a2b34e0b71_train_data.json
43
+ ds_type: json
44
+ format: custom
45
+ path: /workspace/input_data/17fc88a2b34e0b71_train_data.json
46
+ type:
47
+ field_input: repo_name
48
+ field_instruction: path
49
+ field_output: content
50
+ format: '{instruction} {input}'
51
+ no_input_format: '{instruction}'
52
+ system_format: '{system}'
53
+ system_prompt: ''
54
+ debug: null
55
+ deepspeed: null
56
+ device: cuda
57
+ early_stopping_patience: 1
58
+ eval_max_new_tokens: 128
59
+ eval_steps: 5
60
+ eval_table_size: null
61
+ evals_per_epoch: null
62
+ flash_attention: false
63
+ fp16: null
64
+ gradient_accumulation_steps: 4
65
+ gradient_checkpointing: true
66
+ group_by_length: false
67
+ hub_model_id: joboffer/8a88bad2-f185-4581-848c-17a0164a60b7
68
+ hub_repo: null
69
+ hub_strategy: checkpoint
70
+ hub_token: null
71
+ learning_rate: 0.0001
72
+ load_in_4bit: false
73
+ load_in_8bit: false
74
+ local_rank: null
75
+ logging_steps: 3
76
+ lora_alpha: 32
77
+ lora_dropout: 0.05
78
+ lora_fan_in_fan_out: null
79
+ lora_model_dir: null
80
+ lora_r: 16
81
+ lora_target_linear: true
82
+ lr_scheduler: cosine
83
+ max_memory:
84
+ 0: 80GiB
85
+ max_steps: 30
86
+ micro_batch_size: 2
87
+ mlflow_experiment_name: /tmp/17fc88a2b34e0b71_train_data.json
88
+ model_type: AutoModelForCausalLM
89
+ num_epochs: 1
90
+ optimizer: adamw_torch
91
+ output_dir: miner_id_24
92
+ pad_to_sequence_len: true
93
+ resume_from_checkpoint: null
94
+ s2_attention: null
95
+ sample_packing: false
96
+ save_steps: 10
97
+ sequence_len: 2048
98
+ strict: false
99
+ tf32: false
100
+ tokenizer_type: AutoTokenizer
101
+ train_on_inputs: true
102
+ trust_remote_code: true
103
+ val_set_size: 0.05
104
+ wandb_entity: null
105
+ wandb_mode: online
106
+ wandb_name: 23ada34b-aa21-426c-83a9-14a74929231e
107
+ wandb_project: Gradients-On-Demand
108
+ wandb_run: your_name
109
+ wandb_runid: 23ada34b-aa21-426c-83a9-14a74929231e
110
+ warmup_steps: 5
111
+ weight_decay: 0.01
112
+ xformers_attention: true
113
+
114
+ ```
115
+
116
+ </details><br>
117
+
118
+ # 8a88bad2-f185-4581-848c-17a0164a60b7
119
+
120
+ This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset.
121
+ It achieves the following results on the evaluation set:
122
+ - Loss: 1.0507
123
+
124
+ ## Model description
125
+
126
+ More information needed
127
+
128
+ ## Intended uses & limitations
129
+
130
+ More information needed
131
+
132
+ ## Training and evaluation data
133
+
134
+ More information needed
135
+
136
+ ## Training procedure
137
+
138
+ ### Training hyperparameters
139
+
140
+ The following hyperparameters were used during training:
141
+ - learning_rate: 0.0001
142
+ - train_batch_size: 2
143
+ - eval_batch_size: 2
144
+ - seed: 42
145
+ - gradient_accumulation_steps: 4
146
+ - total_train_batch_size: 8
147
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
148
+ - lr_scheduler_type: cosine
149
+ - lr_scheduler_warmup_steps: 5
150
+ - training_steps: 30
151
+
152
+ ### Training results
153
+
154
+ | Training Loss | Epoch | Step | Validation Loss |
155
+ |:-------------:|:------:|:----:|:---------------:|
156
+ | No log | 0.0027 | 1 | 1.0707 |
157
+ | 1.0383 | 0.0135 | 5 | 1.0691 |
158
+ | 1.032 | 0.0270 | 10 | 1.0626 |
159
+ | 1.1076 | 0.0405 | 15 | 1.0567 |
160
+ | 1.0528 | 0.0539 | 20 | 1.0528 |
161
+ | 0.9893 | 0.0674 | 25 | 1.0510 |
162
+ | 1.0197 | 0.0809 | 30 | 1.0507 |
163
+
164
+
165
+ ### Framework versions
166
+
167
+ - PEFT 0.13.2
168
+ - Transformers 4.46.0
169
+ - Pytorch 2.5.0+cu124
170
+ - Datasets 3.0.1
171
  - Tokenizers 0.20.1