End of training

README.md

@@ -0,0 +1,57 @@
+---
+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.
+
+## 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: 0.0001
+- 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
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.38.1
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "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,
+  "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": [
+    "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 sha256:16390cebb287be889e79585bde85d57f468fc36f65c70b55f1d0d097f447b070
+size 47237856

trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0008022398536714506,
+  "eval_steps": 100,
+  "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": 7.037811279296875,
+      "learning_rate": 8e-05,
+      "loss": 2.3007,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.989239692687988,
+      "learning_rate": 6e-05,
+      "loss": 1.0676,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.793990612030029,
+      "learning_rate": 4e-05,
+      "loss": 0.5856,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.514509439468384,
+      "learning_rate": 2e-05,
+      "loss": 0.5141,
+      "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.3384485244750977,
+      "learning_rate": 0.0,
+      "loss": 0.5086,
+      "step": 25
+    },
+    {
+      "epoch": 0.0,
+      "step": 25,
+      "total_flos": 479173072435200.0,
+      "train_loss": 0.9953355026245118,
+      "train_runtime": 114.2038,
+      "train_samples_per_second": 1.751,
+      "train_steps_per_second": 0.219
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 479173072435200.0,
+  "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 sha256:86d79e6b7d1aab02a1825bc0c5348023dbfff7db1a84e1bfca25f13f7971a015
+size 4856