Upload 6 files

README.md

@@ -1,3 +1,9 @@
----
-license: cc-by-nc-4.0
----
+---
+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-13b-v1.5",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd29ec07484c26bf3c85e840232fe3e3ac16631324644a2ea404a2a5173c3d9b
+size 1001584333

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "lmsys/vicuna-13b-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "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-patch14-336",
+  "model_type": "llava",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "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 sha256:856f0a5fdfbb8c210d828987f24e68a9ed5cfbe7a681ac46c0ead69aa9a1dae1
+size 62936807

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 8,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002,
+      "loss": 1.4809,
+      "step": 1
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.4582,
+      "step": 2
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 1.2343,
+      "step": 3
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 1.1173,
+      "step": 4
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 1.0159,
+      "step": 5
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.9748,
+      "step": 6
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 0.9348,
+      "step": 7
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.9422,
+      "step": 8
+    },
+    {
+      "epoch": 1.0,
+      "step": 8,
+      "total_flos": 9228393381888.0,
+      "train_loss": 1.1448063105344772,
+      "train_runtime": 181.8282,
+      "train_samples_per_second": 5.5,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "max_steps": 8,
+  "num_train_epochs": 1,
+  "total_flos": 9228393381888.0,
+  "trial_name": null,
+  "trial_params": null
+}