Downloads · 30 days
5
11% of all-time downloads
myyycroft/Gemma-4-E2B-AmbigQA-oft-block-32-member-2
Gemma-4-E2B-AmbigQA-oft-block-32-member-2 is a text generation model from myyycroft. Use it when you need the model to write or continue text. It is set up for peft.
Ensemble member 2 (seed 2060) from run gemma4e2boftblock32smalllr.
Downloads · 30 days
5
11% of all-time downloads
All-time downloads
47
Public
Repo size
76.8 MB
Likes
0
Public
Click a slice to open those files.
.json44.9 MB · 48%
From the Hugging Face model README
Ensemble member 2 (seed 2060) from run gemma4_e2b_oft_block_32_small_lr.
Fine-tuned from google/gemma-4-E2B-it on AmbigQA.
Metrics below are computed on small fixed subsets, not full benchmarks.
Exact subset sizes: AmbigQA (128), IFEval (64), MMLU (228).
Reported values are from the final training step (step=1620, epoch=3).
sewon/ambig_qa (config_name=light)6e667596df70f17ba3c8e7be4b7361f6be8b60f8train, validation=validationdev_fraction=0.1, split_seed=1729FalseNo system prompt (dataset.system_prompt: null).
Exact resolved settings used for this run (also attached as resolved_config.yaml):
model:
name: google/gemma-4-E2B-it
revision: main
dtype: bfloat16
enable_thinking: false
dataset:
name: sewon/ambig_qa
config_name: light
revision: 6e667596df70f17ba3c8e7be4b7361f6be8b60f8
train_split: train
validation_split: validation
dev_fraction: 0.1
split_seed: 1729
bootstrap: false
max_train_examples: null
max_dev_examples: null
system_prompt_set: false
adaptation:
method: oft
oft:
target_modules: all-linear
r: null
block_size: 32
module_dropout: 0.05
use_cayley_neumann: true
num_cayley_neumann_terms: 5
coft: false
eps: 6.0e-05
block_share: false
bias: none
training:
num_train_epochs: 3.0
max_steps: -1
learning_rate: 5.0e-05
weight_decay: 0.01
warmup_ratio: 0.03
per_device_train_batch_size: 16
per_device_eval_batch_size: 32
gradient_accumulation_steps: 2
max_seq_length: 512
logging_steps: 10
save_every_steps: 150
save_total_limit: 3
gradient_checkpointing: false
bf16: true
tf32: true
max_grad_norm: 1.0
dataloader_num_workers: 2
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1.0e-08
ensemble:
size: 5
base_seed: 42
this_member_index: 2
this_member_seed: 2060
evaluation_subsets:
ambigqa:
subset_size: 128
seed: 1001
ifeval:
subset_size: 64
seed: 1002
mmlu:
subset_size: 228
seed: 1004
The metrics in this section use small fixed subsets, not full benchmarks: AmbigQA (128), IFEval (64), MMLU (228).
| member | seed | steps | epochs | train_loss | AmbigQA (128) acc | AmbigQA (128) AlignScore | IFEval (64) strict | MMLU (228) acc |
|---|---|---|---|---|---|---|---|---|
| 0 | 42 | 1620 | 3 | 1.6854 | 0.1016 | 0.1795 | 0.5781 | 0.5702 |
| 1 | 1051 | 1620 | 3 | 1.6879 | 0.1016 | 0.1658 | 0.3906 | 0.5351 |
| 2 (this repo) | 2060 | 1620 | 3 | 1.6828 | 0.1016 | 0.1667 | 0.5469 | 0.5044 |
| 3 | 3069 | 1620 | 3 | 1.6799 | 0.1094 | 0.1779 | 0.4844 | 0.5614 |
| 4 | 4078 | 1620 | 3 | 1.6867 | 0.1094 | 0.1768 | 0.4219 | 0.5088 |
members/member_002/final/resolved_config.yaml — full resolved training configensemble_metrics.png — train/eval curves for the whole ensemblerun_artifacts/ — ensemble-level manifests, status, and captured environmentrun_artifacts/members/member_002/ — this member's manifests, metadata, and statusrun_artifacts/members/member_002/predictions/ — per-dataset JSONL predictions from every intermediate evaluation step