trungtienluong/test_5

README.md

@@ -0,0 +1,73 @@
+---
+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: 0.3252
+
+## 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: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3186        | 0.88  | 50   | 0.2878          |
+| 0.2214        | 1.77  | 100  | 0.2463          |
+| 0.1555        | 2.65  | 150  | 0.2328          |
+| 0.0922        | 3.54  | 200  | 0.2362          |
+| 0.0659        | 4.42  | 250  | 0.2527          |
+| 0.0373        | 5.31  | 300  | 0.2691          |
+| 0.0282        | 6.19  | 350  | 0.2968          |
+| 0.0268        | 7.08  | 400  | 0.2900          |
+| 0.0251        | 7.96  | 450  | 0.3078          |
+| 0.0207        | 8.85  | 500  | 0.3252          |
+| 0.0198        | 9.73  | 550  | 0.3269          |
+
+
+### 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": [
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "o_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 sha256:1779b227035a6370e1db40b6d77f8d456dac38b43f2ace4ba354a8dc397763f9
+size 167832240

runs/Jun08_07-26-54_e7dde5cc7aa0/events.out.tfevents.1717831620.e7dde5cc7aa0.233.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c803afedbaa8f23d32ac8b90f08712ae022ef4fa868de1801c2d5ce6d8cc21b4
+size 16874

runs/Jun08_07-26-54_e7dde5cc7aa0/events.out.tfevents.1717840443.e7dde5cc7aa0.233.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc6fafcc92a4bd1dbc5983c56fd5547151269aed8bf43530202ff19f5071724
+size 359

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e685872c8f5d6d59a3f2e0669f37553fc5de50767c4775b5ecd9eb219716fe12
+size 4728