Views
No views yet

Upon the shore of time,
Where waves of years do beat,
I stood and watched as they climb
The cliffs of eternity.
In every cresting o'er the deep,
A life was borne upon the tide;
Each wave that did break at my feet,
Did bear away some soul that had died.
And yet, amidst all this great throng,
There came to me a voice soft and low:
"O mortal man! What seekest thou here?"
Then answered I: "I seek the path of woe."
"Thou seekest," quoth she, "that which is lost;
For lo! The waves have borne it away.
Seek not then for that which once was thine own,
But rather turn thy face towards the light of day."
And so saying, away did she go,
Leaving me alone upon the shore.
Then turned I my steps unto mine own home,
And left behind me all thoughts of sorrow and of woe.Upon the canvas of the azure sky,
The sun doth paint his golden chariot's course.
His radiant beams like arrows fly,
And pierce the clouds with light's resplendent force.
The verdant fields in emerald array,
Reflect the glory of his noontide reign;
While every blossom, bathed in warm display,
Exhales its sweet perfume on the plain.
But lo! as evening's purple curtain falls,
The sun doth sink behind the western hill.
His parting rays like lovers' farewell calls,
And gilds the heavens with a rosy thrill.
Then let us praise this daily wondrous sight,
And bless the Maker of the world so bright.0.4.11base_model: MarinaraSpaghetti/NemoMix-Unleashed-12B
2model_type: AutoModelForCausalLM
3tokenizer_type: AutoTokenizer
4trust_remote_code: true
5
6save_safetensors: true
7
8load_in_8bit: false
9load_in_4bit: true
10strict: false
11
12special_tokens:
13 pad_token: <pad>
14
15rl: dpo
16# total_num_tokens:
17datasets:
18 - path: jondurbin/gutenberg-dpo-v0.1
19 split: train
20 type:
21 field_system: system
22 field_prompt: prompt
23 field_chosen: chosen
24 field_rejected: rejected
25 prompt_format: "[INST]{prompt}[/INST]"
26 chosen_format: "{chosen}"
27 rejected_format: "{rejected}"
28 - path: unalignment/toxic-dpo-v0.2
29 split: train
30 type:
31 field_system: system
32 field_prompt: prompt
33 field_chosen: chosen
34 field_rejected: rejected
35 prompt_format: "[INST]{prompt}[/INST]"
36 chosen_format: "{chosen}"
37 rejected_format: "{rejected}"
38
39dataset_prepared_path: prepared-dpo
40output_dir: ./dpoq
41val_set_size: 0.001
42
43seed: 1
44
45sequence_len: 2048
46sample_packing: false
47eval_sample_packing: false
48pad_to_sequence_len: false
49
50chat_template: inst
51
52adapter: qlora
53lora_model_dir:
54lora_r: 256
55lora_alpha: 256
56lora_dropout: 0.05
57lora_target_linear: true
58lora_fan_in_fan_out:
59peft_use_dora: true
60
61wandb_project: unleashed-qlora-dpo
62wandb_entity:
63wandb_watch:
64wandb_name:
65wandb_log_model:
66
67gradient_accumulation_steps: 16
68micro_batch_size: 1
69num_epochs: 1
70optimizer: paged_adamw_8bit
71lr_scheduler: cosine
72learning_rate: 0.00002
73cosine_min_lr_ratio: 0.1
74cosine_constant_lr_ratio: 0.95
75
76train_on_inputs: false
77group_by_length: false
78bf16: true
79fp16:
80tf32: false
81
82gradient_checkpointing: true
83early_stopping_patience:
84resume_from_checkpoint:
85local_rank:
86logging_steps: 1
87xformers_attention:
88flash_attention: true
89
90warmup_steps: 16
91evals_per_epoch: 8
92saves_per_epoch: 8
93save_total_limit: 2
94debug:
95deepspeed:
96weight_decay: 0.001
97fsdp:
98fsdp_config:
99