trungtienluong/test_5

README.md

@@ -0,0 +1,67 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: HuggingFaceH4/zephyr-7b-beta
+model-index:
+- name: experiments500czephymodel
+  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. -->
+
+# experiments500czephymodel
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2464
+
+## 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: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3307        | 0.88  | 50   | 0.3085          |
+| 0.231         | 1.77  | 100  | 0.2617          |
+| 0.1649        | 2.65  | 150  | 0.2406          |
+| 0.11          | 3.54  | 200  | 0.2417          |
+| 0.0992        | 4.42  | 250  | 0.2491          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.36.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "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": 32,
+  "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": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "k_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 sha256:4fc157b2b8ae05d1755cd6e3f88e802f8461212c523d033ddcb4db59de852bf5
+size 167832240

runs/Jun11_05-21-53_026fcc72aacf/events.out.tfevents.1718089196.026fcc72aacf.179.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66fc1e501cd54561eb3620d695196c49ade45926db7b7fe39c0c77fa1f0c472
+size 359

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0403d366d8d69f86b1bb455ebb3abb620a6a3f7559fc6a755ce3caf128e01dc
+size 4728