vvduc03/lora-llava-3b

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: liuhaotian/llava-v1.6-mistral-7b
+model-index:
+- name: LLaVA-Mistral-finetuned
+  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. -->
+
+# LLaVA-Mistral-finetuned
+
+This model is a fine-tuned version of [liuhaotian/llava-v1.6-mistral-7b](https://huggingface.co/liuhaotian/llava-v1.6-mistral-7b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- training_steps: 200
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0           | 200.0 | 200  | 0.0000          |
+
+
+### Framework versions
+
+- Transformers 4.42.0.dev0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.19.1
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- _load_in_8bit: False
+- _load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+
+### Framework versions
+
+
+- PEFT 0.6.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlavaMistralForCausalLM",
+    "parent_library": "llava.model.language_model.llava_mistral"
+  },
+  "base_model_name_or_path": "liuhaotian/llava-v1.6-mistral-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943d0f3883083f3d9820d0c1abd7af634249a9b793eae7189fe2599276553575
+size 47237856

trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 200.0,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.38967031240463257,
+      "learning_rate": 8e-05,
+      "loss": 0.1783,
+      "step": 20
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.009602731093764305,
+      "learning_rate": 0.00016,
+      "loss": 0.0093,
+      "step": 40
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.000580370076932013,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 80.0,
+      "grad_norm": 0.00020515041251201183,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 0.00012300981325097382,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 120.0,
+      "grad_norm": 9.383377619087696e-05,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 8.079586405074224e-05,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 160.0,
+      "grad_norm": 7.359922165051103e-05,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 6.797131209168583e-05,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 6.64097024127841e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 200.0,
+      "eval_loss": 1.2874310414190404e-05,
+      "eval_runtime": 0.4025,
+      "eval_samples_per_second": 2.485,
+      "eval_steps_per_second": 2.485,
+      "step": 200
+    },
+    {
+      "epoch": 200.0,
+      "step": 200,
+      "total_flos": 1572670596710400.0,
+      "train_loss": 0.018764802380228502,
+      "train_runtime": 147.4566,
+      "train_samples_per_second": 21.701,
+      "train_steps_per_second": 1.356
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 200,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1572670596710400.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a0369021c64d53315ac38195fdc982e14c3b117e8662c6734eec42e120a343
+size 5112