Alphatao commited on
Commit
ab371b9
·
verified ·
1 Parent(s): 28241ff

End of training

Browse files
Files changed (3) hide show
  1. README.md +183 -0
  2. adapter_model.bin +3 -0
  3. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/gemma-2b-it
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 9d65626e-53aa-48e7-9c43-1cd15808de5a
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/gemma-2b-it
23
+ bf16: true
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 52b51d4a8d8dae82_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/52b51d4a8d8dae82_train_data.json
32
+ type:
33
+ field_instruction: instruction
34
+ field_output: output
35
+ format: '{instruction}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ device_map:
41
+ ? ''
42
+ : 0,1,2,3,4,5,6,7
43
+ early_stopping_patience: 2
44
+ eval_max_new_tokens: 128
45
+ eval_steps: 400
46
+ eval_table_size: null
47
+ flash_attention: false
48
+ gradient_accumulation_steps: 4
49
+ gradient_checkpointing: true
50
+ group_by_length: false
51
+ hub_model_id: Alphatao/9d65626e-53aa-48e7-9c43-1cd15808de5a
52
+ hub_repo: null
53
+ hub_strategy: null
54
+ hub_token: null
55
+ learning_rate: 0.0002
56
+ load_best_model_at_end: true
57
+ load_in_4bit: false
58
+ load_in_8bit: false
59
+ local_rank: null
60
+ logging_steps: 1
61
+ lora_alpha: 32
62
+ lora_dropout: 0.05
63
+ lora_fan_in_fan_out: null
64
+ lora_model_dir: null
65
+ lora_r: 16
66
+ lora_target_linear: true
67
+ lora_target_modules:
68
+ - q_proj
69
+ - k_proj
70
+ - v_proj
71
+ - o_proj
72
+ lr_scheduler: cosine
73
+ max_grad_norm: 1.0
74
+ max_steps: 11867
75
+ micro_batch_size: 2
76
+ mlflow_experiment_name: /tmp/52b51d4a8d8dae82_train_data.json
77
+ model_type: AutoModelForCausalLM
78
+ num_epochs: 10
79
+ optimizer: adamw_bnb_8bit
80
+ output_dir: miner_id_24
81
+ pad_to_sequence_len: true
82
+ resume_from_checkpoint: null
83
+ s2_attention: null
84
+ sample_packing: false
85
+ save_steps: 400
86
+ sequence_len: 1024
87
+ strict: false
88
+ tf32: true
89
+ tokenizer_type: AutoTokenizer
90
+ train_on_inputs: false
91
+ trust_remote_code: true
92
+ val_set_size: 0.05
93
+ wandb_entity: null
94
+ wandb_mode: online
95
+ wandb_name: ff680a59-ee3c-407a-8506-d9507d1c8bd0
96
+ wandb_project: Gradients-On-Demand
97
+ wandb_run: your_name
98
+ wandb_runid: ff680a59-ee3c-407a-8506-d9507d1c8bd0
99
+ warmup_steps: 10
100
+ weight_decay: 0.0
101
+ xformers_attention: null
102
+
103
+ ```
104
+
105
+ </details><br>
106
+
107
+ # 9d65626e-53aa-48e7-9c43-1cd15808de5a
108
+
109
+ This model is a fine-tuned version of [unsloth/gemma-2b-it](https://huggingface.co/unsloth/gemma-2b-it) on the None dataset.
110
+ It achieves the following results on the evaluation set:
111
+ - Loss: 0.7440
112
+
113
+ ## Model description
114
+
115
+ More information needed
116
+
117
+ ## Intended uses & limitations
118
+
119
+ More information needed
120
+
121
+ ## Training and evaluation data
122
+
123
+ More information needed
124
+
125
+ ## Training procedure
126
+
127
+ ### Training hyperparameters
128
+
129
+ The following hyperparameters were used during training:
130
+ - learning_rate: 0.0002
131
+ - train_batch_size: 2
132
+ - eval_batch_size: 2
133
+ - seed: 42
134
+ - gradient_accumulation_steps: 4
135
+ - total_train_batch_size: 8
136
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
137
+ - lr_scheduler_type: cosine
138
+ - lr_scheduler_warmup_steps: 10
139
+ - training_steps: 11867
140
+
141
+ ### Training results
142
+
143
+ | Training Loss | Epoch | Step | Validation Loss |
144
+ |:-------------:|:------:|:-----:|:---------------:|
145
+ | 1.6257 | 0.0001 | 1 | 1.3826 |
146
+ | 0.823 | 0.0341 | 400 | 0.8594 |
147
+ | 0.8278 | 0.0682 | 800 | 0.8445 |
148
+ | 0.9407 | 0.1023 | 1200 | 0.8366 |
149
+ | 0.8239 | 0.1364 | 1600 | 0.8304 |
150
+ | 1.0677 | 0.1705 | 2000 | 0.8265 |
151
+ | 0.8125 | 0.2046 | 2400 | 0.8186 |
152
+ | 0.9515 | 0.2387 | 2800 | 0.8148 |
153
+ | 0.7069 | 0.2727 | 3200 | 0.8099 |
154
+ | 0.7106 | 0.3068 | 3600 | 0.8049 |
155
+ | 0.9589 | 0.3409 | 4000 | 0.8002 |
156
+ | 0.9544 | 0.3750 | 4400 | 0.7965 |
157
+ | 0.833 | 0.4091 | 4800 | 0.7919 |
158
+ | 0.8829 | 0.4432 | 5200 | 0.7867 |
159
+ | 1.0338 | 0.4773 | 5600 | 0.7828 |
160
+ | 0.7217 | 0.5114 | 6000 | 0.7784 |
161
+ | 0.7006 | 0.5455 | 6400 | 0.7739 |
162
+ | 0.8399 | 0.5796 | 6800 | 0.7699 |
163
+ | 0.5234 | 0.6137 | 7200 | 0.7656 |
164
+ | 0.6645 | 0.6478 | 7600 | 0.7614 |
165
+ | 0.8158 | 0.6819 | 8000 | 0.7582 |
166
+ | 0.5981 | 0.7160 | 8400 | 0.7548 |
167
+ | 0.6689 | 0.7501 | 8800 | 0.7522 |
168
+ | 0.854 | 0.7841 | 9200 | 0.7498 |
169
+ | 0.5398 | 0.8182 | 9600 | 0.7478 |
170
+ | 0.7944 | 0.8523 | 10000 | 0.7464 |
171
+ | 1.061 | 0.8864 | 10400 | 0.7452 |
172
+ | 0.7511 | 0.9205 | 10800 | 0.7445 |
173
+ | 0.6627 | 0.9546 | 11200 | 0.7441 |
174
+ | 0.8566 | 0.9887 | 11600 | 0.7440 |
175
+
176
+
177
+ ### Framework versions
178
+
179
+ - PEFT 0.13.2
180
+ - Transformers 4.46.0
181
+ - Pytorch 2.5.0+cu124
182
+ - Datasets 3.0.1
183
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768dad542238371285681e5da1b0a1d0366023e1b5a7e5193cb8c4a5a637cc63
3
+ size 78537274
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00d2f658773df1824ac2ff58f8ba5de2d230671006e18a587ecb46abcd00ab41
3
  size 78480072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb2f6c6c78fedee39c37151854f1bcae6a0405325a6c60735055388aa730973
3
  size 78480072