jssky commited on
Commit
296039a
1 Parent(s): 4306bb9

End of training

Browse files
Files changed (2) hide show
  1. README.md +167 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: katuni4ka/tiny-random-falcon-40b
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: a5daa407-e03b-4c0e-a434-cbfb1f57aff6
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
+ base_model: katuni4ka/tiny-random-falcon-40b
22
+ bf16: false
23
+ chat_template: llama3
24
+ dataset_prepared_path: null
25
+ datasets:
26
+ - data_files:
27
+ - 93d9886916e01068_train_data.json
28
+ ds_type: json
29
+ format: custom
30
+ path: /workspace/input_data/93d9886916e01068_train_data.json
31
+ type:
32
+ field_instruction: utterance
33
+ field_output: semantic_parse
34
+ format: '{instruction}'
35
+ no_input_format: '{instruction}'
36
+ system_format: '{system}'
37
+ system_prompt: ''
38
+ debug: null
39
+ deepspeed: null
40
+ devices:
41
+ - 0
42
+ - 1
43
+ - 2
44
+ - 3
45
+ - 4
46
+ - 5
47
+ - 6
48
+ - 7
49
+ early_stopping_patience: null
50
+ eval_max_new_tokens: 128
51
+ eval_table_size: null
52
+ evals_per_epoch: 4
53
+ flash_attention: false
54
+ fp16: true
55
+ fsdp: null
56
+ fsdp_config: null
57
+ gradient_accumulation_steps: 4
58
+ gradient_checkpointing: false
59
+ group_by_length: false
60
+ hub_model_id: jssky/a5daa407-e03b-4c0e-a434-cbfb1f57aff6
61
+ hub_repo: null
62
+ hub_strategy: checkpoint
63
+ hub_token: null
64
+ learning_rate: 0.0002
65
+ load_in_4bit: false
66
+ load_in_8bit: false
67
+ local_rank: null
68
+ logging_steps: 1
69
+ lora_alpha: 32
70
+ lora_dropout: 0.05
71
+ lora_fan_in_fan_out: null
72
+ lora_model_dir: null
73
+ lora_r: 16
74
+ lora_target_linear: true
75
+ lr_scheduler: cosine
76
+ max_steps: 10
77
+ micro_batch_size: 1
78
+ mlflow_experiment_name: /tmp/93d9886916e01068_train_data.json
79
+ model_type: AutoModelForCausalLM
80
+ num_epochs: 1
81
+ num_gpus: 8
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
+ saves_per_epoch: 4
89
+ sequence_len: 4056
90
+ special_tokens:
91
+ pad_token: <|endoftext|>
92
+ strict: false
93
+ tf32: false
94
+ tokenizer_type: AutoTokenizer
95
+ train_batch_size: 32
96
+ train_on_inputs: false
97
+ trust_remote_code: true
98
+ val_set_size: 0.05
99
+ wandb_entity: null
100
+ wandb_mode: online
101
+ wandb_name: a5daa407-e03b-4c0e-a434-cbfb1f57aff6
102
+ wandb_project: Gradients-On-Demand
103
+ wandb_run: your_name
104
+ wandb_runid: a5daa407-e03b-4c0e-a434-cbfb1f57aff6
105
+ warmup_steps: 10
106
+ weight_decay: 0.0
107
+ xformers_attention: null
108
+
109
+ ```
110
+
111
+ </details><br>
112
+
113
+ # a5daa407-e03b-4c0e-a434-cbfb1f57aff6
114
+
115
+ This model is a fine-tuned version of [katuni4ka/tiny-random-falcon-40b](https://huggingface.co/katuni4ka/tiny-random-falcon-40b) on the None dataset.
116
+ It achieves the following results on the evaluation set:
117
+ - Loss: 11.0403
118
+
119
+ ## Model description
120
+
121
+ More information needed
122
+
123
+ ## Intended uses & limitations
124
+
125
+ More information needed
126
+
127
+ ## Training and evaluation data
128
+
129
+ More information needed
130
+
131
+ ## Training procedure
132
+
133
+ ### Training hyperparameters
134
+
135
+ The following hyperparameters were used during training:
136
+ - learning_rate: 0.0002
137
+ - train_batch_size: 1
138
+ - eval_batch_size: 1
139
+ - seed: 42
140
+ - distributed_type: multi-GPU
141
+ - num_devices: 8
142
+ - gradient_accumulation_steps: 4
143
+ - total_train_batch_size: 32
144
+ - total_eval_batch_size: 8
145
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
146
+ - lr_scheduler_type: cosine
147
+ - lr_scheduler_warmup_steps: 10
148
+ - training_steps: 10
149
+ - mixed_precision_training: Native AMP
150
+
151
+ ### Training results
152
+
153
+ | Training Loss | Epoch | Step | Validation Loss |
154
+ |:-------------:|:------:|:----:|:---------------:|
155
+ | 44.4846 | 0.0001 | 1 | 11.1092 |
156
+ | 44.4614 | 0.0003 | 3 | 11.1038 |
157
+ | 44.4082 | 0.0007 | 6 | 11.0816 |
158
+ | 44.2531 | 0.0010 | 9 | 11.0403 |
159
+
160
+
161
+ ### Framework versions
162
+
163
+ - PEFT 0.13.2
164
+ - Transformers 4.46.0
165
+ - Pytorch 2.5.0+cu124
166
+ - Datasets 3.0.1
167
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42cc8377847a61a39be6fedd66a49d8c8b7c21cf420aec39d9367ce9a413004
3
+ size 252062