Model Card for Model ID
Map: 100%
2920/2920 [00:01<00:00, 1602.09 examples/s]
[365/365 4:25:54]
Test Loss: 1.0123
Step Training Loss Validation Loss
250 0.983800 0.957103
500 0.937900 0.954966
750 0.862300 0.968044
1000 0.800900 0.986456
1250 0.712600 1.017532
1500 0.652100 1.035168
1750 0.600500 1.051357
2000 0.412800 1.152156
2250 0.386200 1.168790
2500 0.377300 1.185837
2750 0.346600 1.223637
3000 0.351300 1.254214
3250 0.321700 1.273642
3500 0.329900 1.280087
train_dataset_transformed = train_dataset_transformed.shuffle(seed=3407)
trainer = SFTTrainer(
model=model,
tokenizer=tokenizer,
train_dataset=train_dataset_transformed,
eval_dataset=val_dataset_transformed,
max_seq_length=max_seq_length,
dataset_num_proc=2,
packing=False,
args=TrainingArguments(
per_device_train_batch_size=8, # Increased batch size
gradient_accumulation_steps=1, # Reduced from 4
warmup_ratio=0.05, # Better than fixed 5 steps for 20K samples
num_train_epochs=2, # Compromise between 1 and 3
learning_rate=1.5e-4, # Try between 1e-4 and 2e-4
fp16=not is_bfloat16_supported(),
bf16=is_bfloat16_supported(),
logging_steps=50,
optim="adamw_8bit",
weight_decay=0.02, # Increased regularization
lr_scheduler_type="cosine_with_restarts",
seed=3407,
output_dir="outputs",
evaluation_strategy="steps",
eval_steps=250, # More frequent validation
save_strategy="steps",
save_steps=250,
load_best_model_at_end=True,
metric_for_best_model="eval_loss", # Changed from "loss"
greater_is_better=False,
),
)
another revise
model = FastLanguageModel.get_peft_model(
model,
r = 32, # Reduced from 64 for better generalization
target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
"gate_proj", "up_proj", "down_proj"],
lora_alpha = 16, # Reduced from 32 (alpha = r/2 is common)
lora_dropout = 0.1, # Slight regularization
bias = "none",
use_gradient_checkpointing = "unsloth",
random_state = 3407,
)
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: [More Information Needed]
- Funded by [optional]: [More Information Needed]
- Shared by [optional]: [More Information Needed]
- Model type: [More Information Needed]
- Language(s) (NLP): [More Information Needed]
- License: [More Information Needed]
- Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
Training Details
Training Data
[More Information Needed]
Training Procedure
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the
Machine Learning Impact calculator presented in
Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]
