dimasik1987 commited on
Commit
cff367b
·
verified ·
1 Parent(s): d19b344

End of training

Browse files
Files changed (2) hide show
  1. README.md +164 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: huggyllama/llama-7b
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: fd33a073-1074-445c-9345-a5b1c5007d55
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: huggyllama/llama-7b
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - e4f54eb5c17207cb_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/e4f54eb5c17207cb_train_data.json
32
+ type:
33
+ field_instruction: sentence1
34
+ field_output: sentence2
35
+ format: '{instruction}'
36
+ no_input_format: '{instruction}'
37
+ system_format: '{system}'
38
+ system_prompt: ''
39
+ debug: null
40
+ deepspeed: null
41
+ early_stopping_patience: null
42
+ eval_max_new_tokens: 128
43
+ eval_table_size: null
44
+ evals_per_epoch: 4
45
+ flash_attention: false
46
+ fp16: null
47
+ fsdp: null
48
+ fsdp_config: null
49
+ gradient_accumulation_steps: 4
50
+ gradient_checkpointing: false
51
+ group_by_length: false
52
+ hub_model_id: dimasik1987/fd33a073-1074-445c-9345-a5b1c5007d55
53
+ hub_repo: null
54
+ hub_strategy: checkpoint
55
+ hub_token: null
56
+ learning_rate: 0.0002
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
+ lr_scheduler: cosine
68
+ max_memory:
69
+ 0: 70GiB
70
+ max_steps: 50
71
+ micro_batch_size: 2
72
+ mlflow_experiment_name: /tmp/e4f54eb5c17207cb_train_data.json
73
+ model_type: AutoModelForCausalLM
74
+ num_epochs: 4
75
+ optimizer: adamw_bnb_8bit
76
+ output_dir: miner_id_24
77
+ pad_to_sequence_len: true
78
+ resume_from_checkpoint: null
79
+ s2_attention: null
80
+ sample_packing: false
81
+ saves_per_epoch: 4
82
+ sequence_len: 1024
83
+ special_tokens:
84
+ pad_token: </s>
85
+ strict: false
86
+ tf32: false
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: fd33a073-1074-445c-9345-a5b1c5007d55
94
+ wandb_project: Gradients-On-Demand
95
+ wandb_run: your_name
96
+ wandb_runid: fd33a073-1074-445c-9345-a5b1c5007d55
97
+ warmup_steps: 10
98
+ weight_decay: 0.0
99
+ xformers_attention: null
100
+
101
+ ```
102
+
103
+ </details><br>
104
+
105
+ # fd33a073-1074-445c-9345-a5b1c5007d55
106
+
107
+ This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on the None dataset.
108
+ It achieves the following results on the evaluation set:
109
+ - Loss: nan
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: 0.0002
129
+ - train_batch_size: 2
130
+ - eval_batch_size: 2
131
+ - seed: 42
132
+ - gradient_accumulation_steps: 4
133
+ - total_train_batch_size: 8
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: cosine
136
+ - lr_scheduler_warmup_steps: 10
137
+ - training_steps: 50
138
+
139
+ ### Training results
140
+
141
+ | Training Loss | Epoch | Step | Validation Loss |
142
+ |:-------------:|:------:|:----:|:---------------:|
143
+ | 0.0 | 0.0004 | 1 | nan |
144
+ | 0.0 | 0.0016 | 4 | nan |
145
+ | 0.0 | 0.0032 | 8 | nan |
146
+ | 0.0 | 0.0047 | 12 | nan |
147
+ | 0.0 | 0.0063 | 16 | nan |
148
+ | 0.0 | 0.0079 | 20 | nan |
149
+ | 0.0 | 0.0095 | 24 | nan |
150
+ | 0.0 | 0.0110 | 28 | nan |
151
+ | 0.0 | 0.0126 | 32 | nan |
152
+ | 0.0 | 0.0142 | 36 | nan |
153
+ | 0.0 | 0.0158 | 40 | nan |
154
+ | 0.0 | 0.0173 | 44 | nan |
155
+ | 0.0 | 0.0189 | 48 | nan |
156
+
157
+
158
+ ### Framework versions
159
+
160
+ - PEFT 0.13.2
161
+ - Transformers 4.46.0
162
+ - Pytorch 2.5.0+cu124
163
+ - Datasets 3.0.1
164
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4b05c55f8078105a1103f3a0b862d9952bd4ac46c835030a8b367fd8b7b3a2
3
+ size 160069834