lesso commited on
Commit
a556c71
1 Parent(s): 1519143

End of training

Browse files
Files changed (2) hide show
  1. README.md +146 -0
  2. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.2
4
+ base_model: unsloth/Llama-3.2-3B
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: a411a2a2-036c-4b0f-9747-7c5e0c9b3409
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/Llama-3.2-3B
23
+ bf16: false
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 171a2b6e29515e8b_train_data.json
29
+ ds_type: json
30
+ field: text
31
+ path: /workspace/input_data/171a2b6e29515e8b_train_data.json
32
+ type: completion
33
+ debug: null
34
+ deepspeed: null
35
+ early_stopping_patience: null
36
+ eval_max_new_tokens: 128
37
+ eval_table_size: null
38
+ evals_per_epoch: 4
39
+ flash_attention: true
40
+ fp16: true
41
+ fsdp: null
42
+ fsdp_config: null
43
+ gradient_accumulation_steps: 4
44
+ gradient_checkpointing: true
45
+ group_by_length: false
46
+ hub_model_id: lesso/a411a2a2-036c-4b0f-9747-7c5e0c9b3409
47
+ hub_repo: null
48
+ hub_strategy: checkpoint
49
+ hub_token: null
50
+ learning_rate: 0.0002
51
+ load_in_4bit: false
52
+ load_in_8bit: false
53
+ local_rank: null
54
+ logging_steps: 1
55
+ lora_alpha: 16
56
+ lora_dropout: 0.05
57
+ lora_fan_in_fan_out: null
58
+ lora_model_dir: null
59
+ lora_r: 8
60
+ lora_target_linear: true
61
+ lr_scheduler: cosine
62
+ max_steps: 10
63
+ micro_batch_size: 1
64
+ mlflow_experiment_name: /tmp/171a2b6e29515e8b_train_data.json
65
+ model_type: AutoModelForCausalLM
66
+ num_epochs: 1
67
+ optimizer: adamw_hf
68
+ output_dir: miner_id_24
69
+ pad_to_sequence_len: true
70
+ resume_from_checkpoint: null
71
+ s2_attention: null
72
+ sample_packing: false
73
+ saves_per_epoch: 4
74
+ sequence_len: 1024
75
+ strict: false
76
+ tf32: false
77
+ tokenizer_type: AutoTokenizer
78
+ train_on_inputs: false
79
+ trust_remote_code: true
80
+ val_set_size: 0.05
81
+ wandb_entity: null
82
+ wandb_mode: online
83
+ wandb_name: a411a2a2-036c-4b0f-9747-7c5e0c9b3409
84
+ wandb_project: Gradients-On-Demand
85
+ wandb_run: your_name
86
+ wandb_runid: a411a2a2-036c-4b0f-9747-7c5e0c9b3409
87
+ warmup_steps: 10
88
+ weight_decay: 0.0
89
+ xformers_attention: null
90
+
91
+ ```
92
+
93
+ </details><br>
94
+
95
+ # a411a2a2-036c-4b0f-9747-7c5e0c9b3409
96
+
97
+ This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset.
98
+ It achieves the following results on the evaluation set:
99
+ - Loss: 2.1493
100
+
101
+ ## Model description
102
+
103
+ More information needed
104
+
105
+ ## Intended uses & limitations
106
+
107
+ More information needed
108
+
109
+ ## Training and evaluation data
110
+
111
+ More information needed
112
+
113
+ ## Training procedure
114
+
115
+ ### Training hyperparameters
116
+
117
+ The following hyperparameters were used during training:
118
+ - learning_rate: 0.0002
119
+ - train_batch_size: 1
120
+ - eval_batch_size: 1
121
+ - seed: 42
122
+ - gradient_accumulation_steps: 4
123
+ - total_train_batch_size: 4
124
+ - optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
125
+ - lr_scheduler_type: cosine
126
+ - lr_scheduler_warmup_steps: 10
127
+ - training_steps: 10
128
+ - mixed_precision_training: Native AMP
129
+
130
+ ### Training results
131
+
132
+ | Training Loss | Epoch | Step | Validation Loss |
133
+ |:-------------:|:------:|:----:|:---------------:|
134
+ | 2.0097 | 0.0002 | 1 | 2.2259 |
135
+ | 2.2435 | 0.0006 | 3 | 2.2232 |
136
+ | 2.2227 | 0.0011 | 6 | 2.2025 |
137
+ | 2.0586 | 0.0017 | 9 | 2.1493 |
138
+
139
+
140
+ ### Framework versions
141
+
142
+ - PEFT 0.13.2
143
+ - Transformers 4.46.0
144
+ - Pytorch 2.5.0+cu124
145
+ - Datasets 3.0.1
146
+ - Tokenizers 0.20.1
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec70435832ddc8de275e5e13d87b6e7817161053faffc578d3c313b65a3dc15
3
+ size 48768810