Views
No views yet
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bittussiiiii/llm-classification-v7a-ensemble-teacher-v1train_v7a_ensemble_teacher_train_ready.csvtarget_label_for_sftPrompt / Response A / Response BA / B / CC means tie1{
2 "model_version": "v7a-ensemble-distill-sft-conservative-seed777-lr8e6",
3 "base_model": "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
4 "hf_v7a_dataset_id": "tussiiiii/llm-classification-v7a-ensemble-teacher-v1",
5 "hf_v7a_train_file": "train_v7a_ensemble_teacher_train_ready.csv",
6 "target_label_source": "target_label_for_sft",
7 "seed": 777,
8 "max_seq_length": 4096,
9 "max_prompt_tokens": 512,
10 "max_resp_tokens": 1536,
11 "use_rationale_input": false,
12 "include_soft_label_text": false,
13 "use_ab_swap_augmentation": true,
14 "final_max_rows": 0,
15 "train_rows_after_processing": 124014,
16 "train_rows": 122773,
17 "valid_rows": 1241,
18 "label_distribution_after_processing": {
19 "A": 43299,
20 "B": 43299,
21 "C": 37416
22 },
23 "label_distribution_train": {
24 "B": 42866,
25 "A": 42866,
26 "C": 37041
27 },
28 "label_distribution_valid": {
29 "B": 433,
30 "A": 433,
31 "C": 375
32 },
33 "lora_r": 64,
34 "lora_alpha": 128,
35 "learning_rate": 8e-06,
36 "weight_decay": 0.05,
37 "per_device_train_bs": 2,
38 "grad_accum": 4,
39 "effective_batch_size": 8,
40 "max_steps": 10000,
41 "num_epochs": 1,
42 "output_dir": "/content/drive/MyDrive/llmcmp_v7a/outputs_train_unsloth_v7a-ensemble-distill-sft-conservative-seed777-lr8e6",
43 "adapter_dir": "/content/drive/MyDrive/llmcmp_v7a/student_adapter_v7a-ensemble-distill-sft-conservative-seed777-lr8e6",
44 "merged_dir": "/content/drive/MyDrive/llmcmp_v7a/student_model_merged_v7a-ensemble-distill-sft-conservative-seed777-lr8e6",
45 "hf_model_id_adapter": "tussiiiii/llmcmp-distill-llama3-8b-lora-v7a-ensemble-distill-sft-conservative-adapter",
46 "hf_model_id_merged": "tussiiiii/llmcmp-distill-llama3-8b-lora-v7a-ensemble-distill-sft-conservative-merged"
47}