Upload 6 files

README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmsys/vicuna-7b-v1.3",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb1aeeb58b57c46c742a003d5fc1153da0136a0df7df16bb4254a3db62150e8
+size 319970957

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "lmsys/vicuna-7b-v1.3",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "square",
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "mm_hidden_size": 1024,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14",
+  "model_type": "llava",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b7ed54cb7ad7ceb3ebda496953ae5aacfd0b634ea97505171ff421207a94ed
+size 8397975

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 2e-05,
+      "loss": 1.25,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.2812,
+      "step": 2
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.2812,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 1.1953,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "step": 4,
+      "total_flos": 402050395406336.0,
+      "train_loss": 1.251953125,
+      "train_runtime": 23.5154,
+      "train_samples_per_second": 2.339,
+      "train_steps_per_second": 0.17
+    }
+  ],
+  "max_steps": 4,
+  "num_train_epochs": 1,
+  "total_flos": 402050395406336.0,
+  "trial_name": null,
+  "trial_params": null
+}