trungtienluong/test_5

README.md

@@ -0,0 +1,58 @@
+---
+license: llama2
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: vilm/vinallama-7b-chat
+model-index:
+- name: experiments_23cau
+  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. -->
+
+# experiments_23cau
+
+This model is a fine-tuned version of [vilm/vinallama-7b-chat](https://huggingface.co/vilm/vinallama-7b-chat) on the None dataset.
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.36.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vilm/vinallama-7b-chat",
+  "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",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "down_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:c26eda101307fa90f867d983d0a28dd15e514ee8b4cc9305e374a1b1dcea23f8
+size 159967880

runs/May27_06-38-47_d34e1570c986/events.out.tfevents.1716791928.d34e1570c986.690.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f976c5424cc191cb59053de77697c2434594a496280599b26af0a9fd0cfe0a
+size 6537

runs/May27_06-40-48_d34e1570c986/events.out.tfevents.1716792048.d34e1570c986.690.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d5881a8754a35361bcc983f7be1dad5d4b7c34f707bd6dc6526e44d9467984
+size 6075

runs/May27_06-42-07_d34e1570c986/events.out.tfevents.1716792128.d34e1570c986.690.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e0dba98af2337682d61a19dfc5f64941012e998aa7776775701bfca784bdb8
+size 6075

runs/May27_06-43-04_d34e1570c986/events.out.tfevents.1716792185.d34e1570c986.690.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb720aadf837759aac1f065c70f73361ec7d1bb9b12c2004401d013150da0419
+size 5451

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f146401428c2c45fc4f7105903bab4e0effbc41b60237d70a49174bf9f52b8b
+size 4664