Upload folder using huggingface_hub

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": "liuhaotian/llava-v1.5-7b",
+  "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",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "v_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 sha256:1a8793dda23484b317fbe9c97b5add4bd1c48e4b80509149a9badab1a2fdcd6e
+size 639787082

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "liuhaotian/llava-v1.5-7b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "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_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": 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:b2ab232df12ada0289917555966e519bd3f14e71538eaa68b7d174010f3e8b6e
+size 41961648

trainer_state.json

@@ -0,0 +1,240 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 35,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001,
+      "loss": 1.41,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0002,
+      "loss": 1.3381,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019954719225730847,
+      "loss": 0.3192,
+      "step": 3
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019819286972627066,
+      "loss": 0.333,
+      "step": 4
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019594929736144976,
+      "loss": 0.3892,
+      "step": 5
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019283679330160726,
+      "loss": 0.2928,
+      "step": 6
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00018888354486549237,
+      "loss": 0.3289,
+      "step": 7
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018412535328311814,
+      "loss": 0.2921,
+      "step": 8
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017860530947427875,
+      "loss": 0.2556,
+      "step": 9
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00017237340381050703,
+      "loss": 0.3128,
+      "step": 10
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016548607339452853,
+      "loss": 0.2491,
+      "step": 11
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015800569095711982,
+      "loss": 0.2943,
+      "step": 12
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2836,
+      "step": 13
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00014154150130018866,
+      "loss": 0.2055,
+      "step": 14
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00013270679633174218,
+      "loss": 0.1871,
+      "step": 15
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00012357589355094275,
+      "loss": 0.2089,
+      "step": 16
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011423148382732853,
+      "loss": 0.2982,
+      "step": 17
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010475819158237425,
+      "loss": 0.1497,
+      "step": 18
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.524180841762577e-05,
+      "loss": 0.2389,
+      "step": 19
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.57685161726715e-05,
+      "loss": 0.2047,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.642410644905726e-05,
+      "loss": 0.1506,
+      "step": 21
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.729320366825784e-05,
+      "loss": 0.1873,
+      "step": 22
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.845849869981137e-05,
+      "loss": 0.1362,
+      "step": 23
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.1933,
+      "step": 24
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.19943090428802e-05,
+      "loss": 0.2071,
+      "step": 25
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.45139266054715e-05,
+      "loss": 0.1955,
+      "step": 26
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7626596189492983e-05,
+      "loss": 0.1245,
+      "step": 27
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.139469052572127e-05,
+      "loss": 0.1603,
+      "step": 28
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.587464671688187e-05,
+      "loss": 0.1888,
+      "step": 29
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.1116455134507664e-05,
+      "loss": 0.17,
+      "step": 30
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.163206698392744e-06,
+      "loss": 0.1368,
+      "step": 31
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.050702638550275e-06,
+      "loss": 0.1649,
+      "step": 32
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8071302737293295e-06,
+      "loss": 0.1879,
+      "step": 33
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.5280774269154115e-07,
+      "loss": 0.1047,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.1412,
+      "step": 35
+    },
+    {
+      "epoch": 1.0,
+      "step": 35,
+      "total_flos": 4772403118080.0,
+      "train_loss": 0.28688187726906367,
+      "train_runtime": 248.2823,
+      "train_samples_per_second": 17.629,
+      "train_steps_per_second": 0.141
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 35,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 4772403118080.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}