pavanyadav/deepseek-r1-distill-qwen-1.5b-ins

README.md

@@ -0,0 +1,82 @@
+---
+library_name: peft
+license: mit
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+tags:
+- generated_from_trainer
+model-index:
+- name: deepseek_finetuned
+  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. -->
+
+# deepseek_finetuned
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3560
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- 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
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.926         | 0.1429 | 100  | 1.3948          |
+| 0.6639        | 0.2857 | 200  | 0.4467          |
+| 0.4304        | 0.4286 | 300  | 0.4228          |
+| 0.4158        | 0.5714 | 400  | 0.4118          |
+| 0.4046        | 0.7143 | 500  | 0.4031          |
+| 0.3968        | 0.8571 | 600  | 0.3952          |
+| 0.3925        | 1.0    | 700  | 0.3888          |
+| 0.3864        | 1.1429 | 800  | 0.3834          |
+| 0.3781        | 1.2857 | 900  | 0.3785          |
+| 0.3759        | 1.4286 | 1000 | 0.3743          |
+| 0.3696        | 1.5714 | 1100 | 0.3708          |
+| 0.3679        | 1.7143 | 1200 | 0.3675          |
+| 0.3664        | 1.8571 | 1300 | 0.3647          |
+| 0.3637        | 2.0    | 1400 | 0.3626          |
+| 0.3607        | 2.1429 | 1500 | 0.3607          |
+| 0.3573        | 2.2857 | 1600 | 0.3592          |
+| 0.3607        | 2.4286 | 1700 | 0.3580          |
+| 0.3561        | 2.5714 | 1800 | 0.3571          |
+| 0.357         | 2.7143 | 1900 | 0.3564          |
+| 0.354         | 2.8571 | 2000 | 0.3561          |
+| 0.3548        | 3.0    | 2100 | 0.3560          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.48.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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:c44260a945ac827cbdbcadf78a94d7394610167c19b41775673f9d4043a95d68
+size 4372840

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f447ec453794fa1ea56627e7a983888bfc87cde8c42720f52e040de20d0f93d
+size 5304