End of training

README.md

@@ -0,0 +1,63 @@
+---
+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: 0.6291
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 25
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7239        | 0.0   | 10   | 0.6832          |
+| 0.7502        | 0.01  | 20   | 0.6291          |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.1
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "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,
+  "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": [
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41d2c53cb89ec7c562baac33c09f2cf1b7a2f4471c18affc120611fe562cc56
+size 47237856

trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0064865566114228265,
+  "eval_steps": 10,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 7.601585865020752,
+      "learning_rate": 0.00016,
+      "loss": 1.629,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 6.085068702697754,
+      "learning_rate": 0.00012,
+      "loss": 0.7239,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 0.6832157969474792,
+      "eval_runtime": 7374.2039,
+      "eval_samples_per_second": 0.481,
+      "eval_steps_per_second": 0.481,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.401209831237793,
+      "learning_rate": 8e-05,
+      "loss": 0.6425,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.414715051651001,
+      "learning_rate": 4e-05,
+      "loss": 0.7502,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 0.6290897130966187,
+      "eval_runtime": 7374.3989,
+      "eval_samples_per_second": 0.481,
+      "eval_steps_per_second": 0.481,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.3705151081085205,
+      "learning_rate": 0.0,
+      "loss": 0.5581,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "step": 25,
+      "total_flos": 832443140849664.0,
+      "train_loss": 0.8607504749298096,
+      "train_runtime": 15509.9229,
+      "train_samples_per_second": 0.013,
+      "train_steps_per_second": 0.002
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 832443140849664.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cba62bab46b248bf1e2e9c708d90f9c23d3487188ce8cbf97865942356a096
+size 4856