Model save

README.md

@@ -5,14 +5,14 @@ base_model: meta-llama/Llama-3.2-1B-Instruct
 tags:
 - generated_from_trainer
 model-index:
-- name: Lumen-Seed-v20
+- name: Lumen-Seed-v30
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Lumen-Seed-v20
+# Lumen-Seed-v30
 
 This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown dataset.
 
@@ -33,14 +33,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 16
+- learning_rate: 0.0002
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 128
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
 - num_epochs: 2
 
@@ -50,8 +48,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.7.1
+- PEFT 0.15.2
 - Transformers 4.52.1
-- Pytorch 2.5.1
-- Datasets 3.6.0
+- Pytorch 2.2.0+cu121
+- Datasets 3.3.1
 - Tokenizers 0.21.1

runs/May23_16-52-41_ip-10-78-145-115.ec2.internal/events.out.tfevents.1748019162.ip-10-78-145-115.ec2.internal.992208.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52271d26ac880bac289c252e5c111751a1191db02e194ecc92593559650286a9
-size 343402
+oid sha256:8d2a54438d557ed0672fd6b007b5ccf4051ebb2c7c84ba7159b6bd78daec02df
+size 343613