AiAF / UFOs-Pretraining-V1

huggingface.co
Total runs: 7
24-hour runs: 0
7-day runs: -1
30-day runs: 1
Model's Last Updated: February 10 2025
text-generation

Introduction of UFOs-Pretraining-V1

Model Details of UFOs-Pretraining-V1

Built with Axolotl

See axolotl config

axolotl version: 0.6.0

base_model: mistralai/Mistral-7B-v0.1
# optionally might have model_type or tokenizer_type
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
# Automatically upload checkpoint and final model to HF
hub_model_id: AiAF/UFOs-Pretraining-V1

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: AiAF/pretraining.jsonl
    type: completion

dataset_prepared_path:
val_set_size: 0.05
output_dir: ./outputs/out

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

max_steps: 100000

wandb_project: "UFO_LLM_Pretraining"
wandb_entity:
wandb_watch: "all"
wandb_name: "UFO_LLM_Pretraining-V1.0"
wandb_log_model: "false"

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

UFOs-Pretraining-V1

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the AiAF/pretraining.jsonl dataset. It achieves the following results on the evaluation set:

  • Loss: 1.6503
Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure
Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-06
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 36
Training results
Training Loss Epoch Step Validation Loss
1.7686 0.1111 1 1.6895
2.0582 0.3333 3 1.6884
1.9135 0.6667 6 1.6793
1.8261 1.0 9 1.6667
1.8757 1.3333 12 1.6570
1.8754 1.6667 15 1.6501
1.8426 2.0 18 1.6468
1.7298 2.3333 21 1.6536
1.4421 2.6667 24 1.6518
1.7533 3.0 27 1.6490
1.5505 3.3333 30 1.6498
1.4142 3.6667 33 1.6500
1.6097 4.0 36 1.6503
Framework versions
  • Transformers 4.48.3
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0

Runs of AiAF UFOs-Pretraining-V1 on huggingface.co

7
Total runs
0
24-hour runs
-1
3-day runs
-1
7-day runs
1
30-day runs

More Information About UFOs-Pretraining-V1 huggingface.co Model

More UFOs-Pretraining-V1 license Visit here:

https://choosealicense.com/licenses/apache-2.0

UFOs-Pretraining-V1 huggingface.co

UFOs-Pretraining-V1 huggingface.co is an AI model on huggingface.co that provides UFOs-Pretraining-V1's model effect (), which can be used instantly with this AiAF UFOs-Pretraining-V1 model. huggingface.co supports a free trial of the UFOs-Pretraining-V1 model, and also provides paid use of the UFOs-Pretraining-V1. Support call UFOs-Pretraining-V1 model through api, including Node.js, Python, http.

UFOs-Pretraining-V1 huggingface.co Url

https://huggingface.co/AiAF/UFOs-Pretraining-V1

AiAF UFOs-Pretraining-V1 online free

UFOs-Pretraining-V1 huggingface.co is an online trial and call api platform, which integrates UFOs-Pretraining-V1's modeling effects, including api services, and provides a free online trial of UFOs-Pretraining-V1, you can try UFOs-Pretraining-V1 online for free by clicking the link below.

AiAF UFOs-Pretraining-V1 online free url in huggingface.co:

https://huggingface.co/AiAF/UFOs-Pretraining-V1

UFOs-Pretraining-V1 install

UFOs-Pretraining-V1 is an open source model from GitHub that offers a free installation service, and any user can find UFOs-Pretraining-V1 on GitHub to install. At the same time, huggingface.co provides the effect of UFOs-Pretraining-V1 install, users can directly use UFOs-Pretraining-V1 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

UFOs-Pretraining-V1 install url in huggingface.co:

https://huggingface.co/AiAF/UFOs-Pretraining-V1

Url of UFOs-Pretraining-V1

UFOs-Pretraining-V1 huggingface.co Url

Provider of UFOs-Pretraining-V1 huggingface.co

AiAF
ORGANIZATIONS

Other API from AiAF

huggingface.co

Total runs: 18
Run Growth: 0
Growth Rate: 0.00%
Updated:October 18 2025
huggingface.co

Total runs: 18
Run Growth: 4
Growth Rate: 22.22%
Updated:April 01 2026
huggingface.co

Total runs: 12
Run Growth: -1
Growth Rate: -8.33%
Updated:January 25 2025
huggingface.co

Total runs: 10
Run Growth: 6
Growth Rate: 60.00%
Updated:May 30 2026