Views
No views yet
0.4.11adapter: lora
2base_model: samoline/7a912e76-d3e1-4ebc-b427-cdfa5be42d9b
3bf16: auto
4chat_template: llama3
5dataset_prepared_path: null
6datasets:
7- data_files:
8 - train_a3d434dc-7bce-43c1-8998-2fa226e7682e.json
9 ds_type: json
10 format: custom
11 path: /workspace/input_data/train_a3d434dc-7bce-43c1-8998-2fa226e7682e.json
12 type:
13 field_instruction: instruction
14 field_output: response
15 format: '{instruction}'
16 no_input_format: '{instruction}'
17 system_format: '{system}'
18 system_prompt: ''
19debug: null
20deepspeed: null
21device_map: auto
22do_eval: true
23early_stopping_patience: 2
24eval_batch_size: 4
25eval_max_new_tokens: 128
26eval_steps: 200
27eval_table_size: null
28evals_per_epoch: null
29flash_attention: true
30fp16: false
31fsdp: null
32fsdp_config: null
33gradient_accumulation_steps: 4
34gradient_checkpointing: false
35group_by_length: true
36hub_model_id: clarxus/63d7244c-8995-4c0b-b618-e353c30a0d54
37hub_repo: null
38hub_strategy: end
39hub_token: null
40learning_rate: 0.0002
41load_in_4bit: false
42load_in_8bit: false
43local_rank: null
44logging_steps: 50
45lora_alpha: 64
46lora_dropout: 0.05
47lora_fan_in_fan_out: null
48lora_model_dir: null
49lora_r: 32
50lora_target_linear: true
51lr_scheduler: constant
52max_grad_norm: 1.0
53max_memory:
54 0: 75GB
55max_steps: 500
56micro_batch_size: 4
57mlflow_experiment_name: /tmp/train_a3d434dc-7bce-43c1-8998-2fa226e7682e.json
58model_type: AutoModelForCausalLM
59num_epochs: 10
60optim_args:
61 adam_beta1: 0.9
62 adam_beta2: 0.95
63 adam_epsilon: 1e-5
64optimizer: adamw_bnb_8bit
65output_dir: miner_id_24
66pad_to_sequence_len: true
67resume_from_checkpoint: null
68s2_attention: null
69sample_packing: false
70save_steps: 200
71saves_per_epoch: null
72sequence_len: 512
73special_tokens:
74 pad_token: <|endoftext|>
75strict: false
76tf32: true
77tokenizer_type: AutoTokenizer
78train_on_inputs: false
79trust_remote_code: true
80val_set_size: 0.05
81wandb_entity: techspear-hub
82wandb_mode: online
83wandb_name: ed0754fa-bbcf-4db9-a716-ccc1dd6683e8
84wandb_project: Gradients-On-Seven
85wandb_run: your_name
86wandb_runid: ed0754fa-bbcf-4db9-a716-ccc1dd6683e8
87warmup_steps: 50
88weight_decay: 0.0
89xformers_attention: null
90| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0000 | 1 | 1.6974 |
| 0.9923 | 0.0013 | 200 | 1.1370 |
| 0.9977 | 0.0027 | 400 | 1.0725 |