Hugging Face's logo

besimray
/
miner1_3b9799d7-12b3-4975-ab6f-be3bd7705350_1731029029

PEFT
Safetensors
falcon
axolotl
Generated from Trainer
custom_code
8-bit precision
bitsandbytes
Model card Files Community
besimray commited on
Commit
464308f
·
verified ·
1 Parent(s): 918b11a

End of training

Browse files
Files changed (2) hide show
  1. README.md +222 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: fxmarty/really-tiny-falcon-testing
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: miner1_3b9799d7-12b3-4975-ab6f-be3bd7705350_1731029029
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: fxmarty/really-tiny-falcon-testing
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - ultrafeedback_binarized_cleaned_train_data.json
29
+ ds_type: json
30
+ path: /workspace/input_data/ultrafeedback_binarized_cleaned_train_data.json
31
+ type:
32
+ field_input: source
33
+ field_instruction: prompt
34
+ field_output: prompt_id
35
+ system_format: '{system}'
36
+ system_prompt: ''
37
+ debug: null
38
+ deepspeed: null
39
+ early_stopping_patience: 1
40
+ eval_max_new_tokens: 128
41
+ eval_steps: 5
42
+ eval_table_size: null
43
+ flash_attention: false
44
+ fp16: null
45
+ fsdp: null
46
+ fsdp_config: null
47
+ gradient_accumulation_steps: 4
48
+ gradient_checkpointing: true
49
+ group_by_length: false
50
+ hours_to_complete: 5
51
+ hub_model_id: besimray/miner1_3b9799d7-12b3-4975-ab6f-be3bd7705350_1731029029
52
+ hub_strategy: checkpoint
53
+ hub_token: null
54
+ learning_rate: 0.0002
55
+ load_in_4bit: false
56
+ load_in_8bit: true
57
+ local_rank: null
58
+ logging_steps: 1
59
+ lora_alpha: 32
60
+ lora_dropout: 0.05
61
+ lora_fan_in_fan_out: null
62
+ lora_model_dir: null
63
+ lora_r: 32
64
+ lora_target_linear: true
65
+ lr_scheduler: cosine
66
+ max_steps: 500
67
+ micro_batch_size: 2
68
+ mlflow_experiment_name: /tmp/ultrafeedback_binarized_cleaned_train_data.json
69
+ model_type: AutoModelForCausalLM
70
+ num_epochs: 4
71
+ optimizer: adamw_bnb_8bit
72
+ output_dir: miner_id_24
73
+ pad_to_sequence_len: true
74
+ resume_from_checkpoint: null
75
+ s2_attention: null
76
+ sample_packing: false
77
+ save_steps: 10
78
+ save_strategy: steps
79
+ sequence_len: 4096
80
+ started_at: '2024-11-08T01:23:49.735921'
81
+ strict: false
82
+ tf32: false
83
+ tokenizer_type: AutoTokenizer
84
+ train_on_inputs: false
85
+ trust_remote_code: true
86
+ val_set_size: 0.05
87
+ wandb_entity: besimray24-rayon
88
+ wandb_mode: online
89
+ wandb_project: Public_TuningSN
90
+ wandb_run: miner_id_24
91
+ wandb_runid: 3b9799d7-12b3-4975-ab6f-be3bd7705350
92
+ warmup_steps: 10
93
+ weight_decay: 0.0
94
+ xformers_attention: null
95
+
96
+ ```
97
+
98
+ </details><br>
99
+
100
+ # miner1_3b9799d7-12b3-4975-ab6f-be3bd7705350_1731029029
101
+
102
+ This model is a fine-tuned version of [fxmarty/really-tiny-falcon-testing](https://huggingface.co/fxmarty/really-tiny-falcon-testing) on the None dataset.
103
+ It achieves the following results on the evaluation set:
104
+ - Loss: 11.0185
105
+
106
+ ## Model description
107
+
108
+ More information needed
109
+
110
+ ## Intended uses & limitations
111
+
112
+ More information needed
113
+
114
+ ## Training and evaluation data
115
+
116
+ More information needed
117
+
118
+ ## Training procedure
119
+
120
+ ### Training hyperparameters
121
+
122
+ The following hyperparameters were used during training:
123
+ - learning_rate: 0.0002
124
+ - train_batch_size: 2
125
+ - eval_batch_size: 2
126
+ - seed: 42
127
+ - gradient_accumulation_steps: 4
128
+ - total_train_batch_size: 8
129
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
130
+ - lr_scheduler_type: cosine
131
+ - lr_scheduler_warmup_steps: 10
132
+ - training_steps: 500
133
+
134
+ ### Training results
135
+
136
+ | Training Loss | Epoch | Step | Validation Loss |
137
+ |:-------------:|:------:|:----:|:---------------:|
138
+ | 44.3865 | 0.0000 | 1 | 11.0934 |
139
+ | 44.389 | 0.0002 | 5 | 11.0931 |
140
+ | 44.3678 | 0.0005 | 10 | 11.0919 |
141
+ | 44.3563 | 0.0007 | 15 | 11.0899 |
142
+ | 44.3507 | 0.0009 | 20 | 11.0876 |
143
+ | 44.3368 | 0.0011 | 25 | 11.0852 |
144
+ | 44.3137 | 0.0014 | 30 | 11.0826 |
145
+ | 44.2998 | 0.0016 | 35 | 11.0797 |
146
+ | 44.3223 | 0.0018 | 40 | 11.0766 |
147
+ | 44.2864 | 0.0020 | 45 | 11.0724 |
148
+ | 44.3044 | 0.0023 | 50 | 11.0679 |
149
+ | 44.2155 | 0.0025 | 55 | 11.0627 |
150
+ | 44.2277 | 0.0027 | 60 | 11.0574 |
151
+ | 44.1989 | 0.0029 | 65 | 11.0519 |
152
+ | 44.1718 | 0.0032 | 70 | 11.0467 |
153
+ | 44.0926 | 0.0034 | 75 | 11.0422 |
154
+ | 44.1955 | 0.0036 | 80 | 11.0389 |
155
+ | 44.1445 | 0.0038 | 85 | 11.0364 |
156
+ | 44.173 | 0.0041 | 90 | 11.0346 |
157
+ | 44.119 | 0.0043 | 95 | 11.0335 |
158
+ | 44.1072 | 0.0045 | 100 | 11.0327 |
159
+ | 44.0926 | 0.0047 | 105 | 11.0319 |
160
+ | 44.1488 | 0.0050 | 110 | 11.0308 |
161
+ | 44.1395 | 0.0052 | 115 | 11.0298 |
162
+ | 44.1485 | 0.0054 | 120 | 11.0291 |
163
+ | 44.1329 | 0.0056 | 125 | 11.0284 |
164
+ | 44.1311 | 0.0059 | 130 | 11.0280 |
165
+ | 44.1152 | 0.0061 | 135 | 11.0274 |
166
+ | 44.1053 | 0.0063 | 140 | 11.0267 |
167
+ | 44.0868 | 0.0066 | 145 | 11.0261 |
168
+ | 44.1361 | 0.0068 | 150 | 11.0255 |
169
+ | 44.1322 | 0.0070 | 155 | 11.0251 |
170
+ | 44.1098 | 0.0072 | 160 | 11.0246 |
171
+ | 44.1007 | 0.0075 | 165 | 11.0242 |
172
+ | 44.0995 | 0.0077 | 170 | 11.0239 |
173
+ | 44.114 | 0.0079 | 175 | 11.0235 |
174
+ | 44.0501 | 0.0081 | 180 | 11.0231 |
175
+ | 44.118 | 0.0084 | 185 | 11.0229 |
176
+ | 44.0967 | 0.0086 | 190 | 11.0228 |
177
+ | 44.1646 | 0.0088 | 195 | 11.0226 |
178
+ | 44.0501 | 0.0090 | 200 | 11.0225 |
179
+ | 44.0946 | 0.0093 | 205 | 11.0222 |
180
+ | 44.047 | 0.0095 | 210 | 11.0219 |
181
+ | 44.0339 | 0.0097 | 215 | 11.0216 |
182
+ | 44.1334 | 0.0099 | 220 | 11.0214 |
183
+ | 44.1315 | 0.0102 | 225 | 11.0212 |
184
+ | 44.0785 | 0.0104 | 230 | 11.0210 |
185
+ | 44.0846 | 0.0106 | 235 | 11.0209 |
186
+ | 44.0812 | 0.0108 | 240 | 11.0208 |
187
+ | 44.0548 | 0.0111 | 245 | 11.0205 |
188
+ | 44.0861 | 0.0113 | 250 | 11.0203 |
189
+ | 44.1121 | 0.0115 | 255 | 11.0202 |
190
+ | 44.0327 | 0.0118 | 260 | 11.0201 |
191
+ | 44.1155 | 0.0120 | 265 | 11.0199 |
192
+ | 44.0547 | 0.0122 | 270 | 11.0198 |
193
+ | 44.0969 | 0.0124 | 275 | 11.0198 |
194
+ | 44.0746 | 0.0127 | 280 | 11.0197 |
195
+ | 44.0535 | 0.0129 | 285 | 11.0195 |
196
+ | 44.1303 | 0.0131 | 290 | 11.0194 |
197
+ | 44.1142 | 0.0133 | 295 | 11.0193 |
198
+ | 44.0685 | 0.0136 | 300 | 11.0192 |
199
+ | 44.1292 | 0.0138 | 305 | 11.0191 |
200
+ | 44.0637 | 0.0140 | 310 | 11.0190 |
201
+ | 44.1035 | 0.0142 | 315 | 11.0189 |
202
+ | 44.0725 | 0.0145 | 320 | 11.0189 |
203
+ | 44.1142 | 0.0147 | 325 | 11.0189 |
204
+ | 44.005 | 0.0149 | 330 | 11.0189 |
205
+ | 44.0686 | 0.0151 | 335 | 11.0188 |
206
+ | 44.059 | 0.0154 | 340 | 11.0187 |
207
+ | 44.0642 | 0.0156 | 345 | 11.0187 |
208
+ | 44.0906 | 0.0158 | 350 | 11.0187 |
209
+ | 44.0386 | 0.0160 | 355 | 11.0186 |
210
+ | 44.0478 | 0.0163 | 360 | 11.0186 |
211
+ | 44.144 | 0.0165 | 365 | 11.0185 |
212
+ | 44.0354 | 0.0167 | 370 | 11.0185 |
213
+ | 44.0702 | 0.0169 | 375 | 11.0185 |
214
+
215
+
216
+ ### Framework versions
217
+
218
+ - PEFT 0.13.2
219
+ - Transformers 4.46.1
220
+ - Pytorch 2.3.1+cu121
221
+ - Datasets 3.0.1
222
+ - Tokenizers 0.20.3
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ddb65f3b6ab3c42cc9bd38fe19b482dce989406fbc746ad5f2072dde030b96
3
+ size 129182