Qwen2.5-Coder-3B-Python-Evaluator-bnb-4bit

README.md

@@ -0,0 +1,72 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-Coder-3B
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B](https://huggingface.co/Qwen/Qwen2.5-Coder-3B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1720
+
+## 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 2
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.3062        | 0.9849 | 49   | 1.2361          |
+| 1.2408        | 1.9849 | 98   | 1.2071          |
+| 1.2022        | 2.9849 | 147  | 1.1921          |
+| 1.1692        | 3.9849 | 196  | 1.1827          |
+| 1.14          | 4.9849 | 245  | 1.1768          |
+| 1.1199        | 5.9849 | 294  | 1.1735          |
+| 1.0947        | 6.9849 | 343  | 1.1710          |
+| 1.0815        | 7.9849 | 392  | 1.1709          |
+| 1.0674        | 8.9849 | 441  | 1.1716          |
+| 1.04          | 9.9849 | 490  | 1.1720          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-3B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd0d86aa856b413b628ad71c1809436c5c179c9c97e369c497a57c78bb8f2af
+size 119801528

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1c286d2ce87b14c58a3b7a311241b5618e803f4b67b958fe5319a6af2a386a
+size 5240