minhdang/math_1-ft

README.md

@@ -0,0 +1,71 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: PrunaAI/deepseek-ai-deepseek-math-7b-rl-bnb-4bit-smashed
+model-index:
+- name: math_ft
+  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. -->
+
+# math_ft
+
+This model is a fine-tuned version of [PrunaAI/deepseek-ai-deepseek-math-7b-rl-bnb-4bit-smashed](https://huggingface.co/PrunaAI/deepseek-ai-deepseek-math-7b-rl-bnb-4bit-smashed) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5111
+
+## 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: 0.0002
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0364        | 0.9655 | 7    | 0.7955          |
+| 0.7271        | 1.9310 | 14   | 0.6199          |
+| 0.604         | 2.8966 | 21   | 0.5675          |
+| 0.4951        | 4.0    | 29   | 0.5419          |
+| 0.5483        | 4.9655 | 36   | 0.5294          |
+| 0.531         | 5.9310 | 43   | 0.5218          |
+| 0.5217        | 6.8966 | 50   | 0.5168          |
+| 0.4511        | 8.0    | 58   | 0.5131          |
+| 0.5083        | 8.9655 | 65   | 0.5115          |
+| 0.4632        | 9.6552 | 70   | 0.5111          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "PrunaAI/deepseek-ai-deepseek-math-7b-rl-bnb-4bit-smashed",
+  "bias": "none",
+  "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_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": [
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_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:a00f4eea28479a830868e9a881c2aeb3928e369bf7eb789247d0dae8a455ee37
+size 149969848

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c61646d4db105c4af0d04d541eea37f7508f140e978714839e73367f18dc739
+size 4984