trungtienluong/test_5

README.md

@@ -0,0 +1,70 @@
+---
+base_model: HuggingFaceH4/zephyr-7b-beta
+library_name: peft
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: experiments500czephymodel_v3
+  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_v3
+
+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: 0.2749
+
+## 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: 2e-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: 8
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3561        | 1.0   | 50   | 0.3625          |
+| 0.2785        | 2.0   | 100  | 0.3014          |
+| 0.1976        | 3.0   | 150  | 0.2770          |
+| 0.1583        | 4.0   | 200  | 0.2718          |
+| 0.1064        | 5.0   | 250  | 0.2785          |
+| 0.0787        | 6.0   | 300  | 0.2934          |
+| 0.0523        | 7.0   | 350  | 0.3087          |
+| 0.0447        | 8.0   | 400  | 0.3199          |
+
+
+### 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": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "q_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 sha256:1b785d835f6ca9040fa854211c9570b0ac02e75db5bdf1f009de2d0d1f8ed89b
+size 167832240

runs/Jul11_11-57-27_f4e41d655abf/events.out.tfevents.1720699054.f4e41d655abf.565.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d3ba418713b010b95161df944386c8b8fbbc29710bb5df2935f55b912b65fb
+size 13557

runs/Jul11_11-57-27_f4e41d655abf/events.out.tfevents.1720706484.f4e41d655abf.565.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d6ad78e5fbae40e9269eee43f287c738a9d2cababaf3b26884e9d4f790485e
+size 901

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a216991c44b9481214e75b32f5edafac94e2ab68ac10de88ced01c74362bbb
+size 4728