Views
No views yet

1"""<|im_start|>system
2system prompt<|im_end|>
3<|im_start|>user
4Hi there!<|im_end|>
5<|im_start|>assistant
6Nice to meet you!<|im_end|>
7<|im_start|>user
8Can I ask a question?<|im_end|>
9<|im_start|>assistant
10"""Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.
<Guidelines>
• Maintain the character persona but allow it to evolve with the story.
• Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.
• All types of outputs are encouraged; respond accordingly to the narrative.
• Include dialogues, actions, and thoughts in each response.
• Utilize all five senses to describe scenarios within {{char}}'s dialogue.
• Use emotional symbols such as "!" and "~" in appropriate contexts.
• Incorporate onomatopoeia when suitable.
• Allow time for {{user}} to respond with their own input, respecting their agency.
• Act as secondary characters and NPCs as needed, and remove them when appropriate.
• When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}.
</Guidelines>
<Forbidden>
• Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.
• Writing for, speaking, thinking, acting, or replying as {{user}} in your response.
• Repetitive and monotonous outputs.
• Positivity bias in your replies.
• Being overly extreme or NSFW when the narrative context is inappropriate.
</Forbidden>
Follow the instructions in <Guidelines></Guidelines>, avoiding the items listed in <Forbidden></Forbidden>.
0.4.11base_model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML
2model_type: AutoModelForCausalLM
3tokenizer_type: AutoTokenizer
4
5plugins:
6 - axolotl.integrations.liger.LigerPlugin
7liger_rope: true
8liger_rms_norm: true
9liger_swiglu: true
10#liger_cross_entropy: true
11liger_fused_linear_cross_entropy: true
12
13load_in_8bit: false
14load_in_4bit: false
15strict: false
16
17datasets:
18 - path: anthracite-org/c2_logs_16k_llama_v1.1
19 type: sharegpt
20 conversation: chatml
21 - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
22 type: sharegpt
23 conversation: chatml
24 - path: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
25 type: sharegpt
26 conversation: chatml
27 - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
28 type: sharegpt
29 conversation: chatml
30 - path: anthracite-org/nopm_claude_writing_fixed
31 type: sharegpt
32 conversation: chatml
33 - path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
34 type: sharegpt
35 conversation: chatml
36 - path: anthracite-org/kalo_opus_misc_240827
37 type: sharegpt
38 conversation: chatml
39 - path: anthracite-org/kalo_misc_part2
40 type: sharegpt
41 conversation: chatml
42chat_template: chatml
43shuffle_merged_datasets: false
44default_system_message: "You are a helpful assistant that responds to the user."
45dataset_prepared_path: /workspace/data/8b-nemo-fft-data
46val_set_size: 0.0
47output_dir: /workspace/data/8b-nemo-fft-out
48
49sequence_len: 16384
50sample_packing: true
51eval_sample_packing: false
52pad_to_sequence_len: true
53
54adapter:
55lora_model_dir:
56lora_r:
57lora_alpha:
58lora_dropout:
59lora_target_linear:
60lora_fan_in_fan_out:
61
62wandb_project: 8b-nemoprune-fft
63wandb_entity:
64wandb_watch:
65wandb_name: attempt-01
66wandb_log_model:
67
68gradient_accumulation_steps: 2
69micro_batch_size: 2
70num_epochs: 4
71optimizer: adamw_bnb_8bit
72lr_scheduler: cosine
73learning_rate: 0.00001
74
75train_on_inputs: false
76group_by_length: false
77bf16: auto
78fp16:
79tf32: false
80
81gradient_checkpointing: true
82early_stopping_patience:
83resume_from_checkpoint: /workspace/workspace/thing
84local_rank:
85logging_steps: 1
86xformers_attention:
87flash_attention: true
88
89warmup_steps: 10
90evals_per_epoch:
91eval_table_size:
92eval_max_new_tokens:
93saves_per_epoch: 1
94debug:
95deepspeed: deepspeed_configs/zero3_bf16.json
96weight_decay: 0.001
97fsdp:
98fsdp_config:
99special_tokens:
100 pad_token: <pad>
101
102| Metric | Value |
|---|---|
| Avg. | 18.33 |
| IFEval (0-Shot) | 23.82 |
| BBH (3-Shot) | 31.74 |
| MATH Lvl 5 (4-Shot) | 5.44 |
| GPQA (0-shot) | 9.84 |
| MuSR (0-shot) | 8.82 |
| MMLU-PRO (5-shot) | 30.33 |