trungtienluong/test_5

README.md

@@ -0,0 +1,67 @@
+---
+base_model: HuggingFaceH4/zephyr-7b-beta
+library_name: peft
+license: mit
+tags:
+- generated_from_trainer
+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: 0.2640
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3153        | 1.0   | 50   | 0.2975          |
+| 0.2205        | 2.0   | 100  | 0.2582          |
+| 0.1677        | 3.0   | 150  | 0.2417          |
+| 0.1077        | 4.0   | 200  | 0.2481          |
+| 0.0901        | 5.0   | 250  | 0.2588          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.36.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- 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": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_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:b85d75fa6a38b69c31398c8708a2aca84d27c1590c4448790e60a1f5b449dde3
+size 167832240

runs/Jul07_13-26-26_d1c40557dd1b/events.out.tfevents.1720358791.d1c40557dd1b.1129.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6521117ddeca5fa400409addf947877790eb391d0e0a0ab5eb7e10e08976b8f4
+size 10380

runs/Jul07_13-26-26_d1c40557dd1b/events.out.tfevents.1720363103.d1c40557dd1b.1129.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851a16335d978d3da1a0a7ae1dd6855ab79907e6400260d77eac3fe65fda095a
+size 901

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8c62f57a43a24bef9b81a329b4cce8636707d86bc1f093a401bf064b32db7d
+size 4728