sergioalves commited on
Commit
6cfc6fc
·
verified ·
1 Parent(s): f98fc72

End of training

Browse files
Files changed (2) hide show
  1. README.md +158 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: jingyeom/seal3.1.6n_7b
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: b961bb9b-7a6d-47e7-b5e4-4b7f8bbf4f94
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: jingyeom/seal3.1.6n_7b
22
+ bf16: auto
23
+ chat_template: llama3
24
+ dataset_prepared_path: null
25
+ datasets:
26
+ - data_files:
27
+ - a1f48e343e632d4d_train_data.json
28
+ ds_type: json
29
+ format: custom
30
+ path: /workspace/input_data/a1f48e343e632d4d_train_data.json
31
+ type:
32
+ field_input: "\u5730\u57DF"
33
+ field_instruction: "\u666F\u6C17\u306E\u73FE\u72B6\u5224\u65AD"
34
+ field_output: "\u8FFD\u52A0\u8AAC\u660E\u53CA\u3073\u5177\u4F53\u7684\u72B6\u6CC1\
35
+ \u306E\u8AAC\u660E"
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: true
53
+ hub_model_id: sergioalves/b961bb9b-7a6d-47e7-b5e4-4b7f8bbf4f94
54
+ hub_repo: null
55
+ hub_strategy: checkpoint
56
+ hub_token: null
57
+ learning_rate: 0.0002
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: 79GiB
71
+ max_steps: 30
72
+ micro_batch_size: 4
73
+ mlflow_experiment_name: /tmp/a1f48e343e632d4d_train_data.json
74
+ model_type: AutoModelForCausalLM
75
+ num_epochs: 1
76
+ optim_args:
77
+ adam_beta1: 0.9
78
+ adam_beta2: 0.95
79
+ adam_epsilon: 1e-5
80
+ optimizer: adamw_torch
81
+ output_dir: miner_id_24
82
+ pad_to_sequence_len: true
83
+ resume_from_checkpoint: null
84
+ s2_attention: null
85
+ sample_packing: false
86
+ save_steps: 10
87
+ sequence_len: 1024
88
+ strict: false
89
+ tf32: false
90
+ tokenizer_type: AutoTokenizer
91
+ train_on_inputs: true
92
+ trust_remote_code: true
93
+ val_set_size: 0.05
94
+ wandb_entity: null
95
+ wandb_mode: online
96
+ wandb_name: 564ac9ba-2a9f-47a1-80f0-3b5121868464
97
+ wandb_project: Gradients-On-Demand
98
+ wandb_run: your_name
99
+ wandb_runid: 564ac9ba-2a9f-47a1-80f0-3b5121868464
100
+ warmup_steps: 5
101
+ weight_decay: 0.001
102
+ xformers_attention: true
103
+
104
+ ```
105
+
106
+ </details><br>
107
+
108
+ # b961bb9b-7a6d-47e7-b5e4-4b7f8bbf4f94
109
+
110
+ This model is a fine-tuned version of [jingyeom/seal3.1.6n_7b](https://huggingface.co/jingyeom/seal3.1.6n_7b) on the None dataset.
111
+ It achieves the following results on the evaluation set:
112
+ - Loss: nan
113
+
114
+ ## Model description
115
+
116
+ More information needed
117
+
118
+ ## Intended uses & limitations
119
+
120
+ More information needed
121
+
122
+ ## Training and evaluation data
123
+
124
+ More information needed
125
+
126
+ ## Training procedure
127
+
128
+ ### Training hyperparameters
129
+
130
+ The following hyperparameters were used during training:
131
+ - learning_rate: 0.0002
132
+ - train_batch_size: 4
133
+ - eval_batch_size: 4
134
+ - seed: 42
135
+ - gradient_accumulation_steps: 4
136
+ - total_train_batch_size: 16
137
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
138
+ - lr_scheduler_type: cosine
139
+ - lr_scheduler_warmup_steps: 5
140
+ - training_steps: 30
141
+
142
+ ### Training results
143
+
144
+ | Training Loss | Epoch | Step | Validation Loss |
145
+ |:-------------:|:------:|:----:|:---------------:|
146
+ | No log | 0.0001 | 1 | nan |
147
+ | 0.0 | 0.0003 | 5 | nan |
148
+ | 0.0 | 0.0005 | 10 | nan |
149
+ | 0.0 | 0.0008 | 15 | nan |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - PEFT 0.13.2
155
+ - Transformers 4.46.0
156
+ - Pytorch 2.5.0+cu124
157
+ - Datasets 3.0.1
158
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c593c6848b5627988047573356ab734f267979f75022189b7e0e5351bef5172
3
+ size 160069834