upload

README.md

@@ -0,0 +1,12 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+- PEFT 0.4.0
+- PEFT 0.4.0
+- PEFT 0.4.0
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/workspace/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": 128,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea1c0eee3823d932ae6b05f4f437c281246e157523628bb7204f1d9d620b6025
+size 319970957

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "/mnt/workspace/llava-v1.5-7b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "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_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": "/mnt/workspace/clip-vit-large-patch14-336",
+  "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-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,
+  "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:f36ea34e146410d35253848d460896e2e24ea77dd661c531d472884c2d8b16ea
+size 41961191

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.8,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002,
+      "loss": 1.2863,
+      "step": 1
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 1.2544,
+      "step": 2
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.0333,
+      "step": 3
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.000178183148246803,
+      "loss": 0.9202,
+      "step": 4
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.8506,
+      "step": 5
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 0.7345,
+      "step": 6
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.6905,
+      "step": 7
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.0001,
+      "loss": 0.6544,
+      "step": 8
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.6118,
+      "step": 9
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 0.5865,
+      "step": 10
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.5699,
+      "step": 11
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 0.505,
+      "step": 12
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 0.4942,
+      "step": 13
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 2.5072087818176382e-06,
+      "loss": 0.5002,
+      "step": 14
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 0.0,
+      "loss": 0.4813,
+      "step": 15
+    },
+    {
+      "epoch": 4.8,
+      "step": 15,
+      "total_flos": 4296337784832.0,
+      "train_loss": 0.7448747992515564,
+      "train_runtime": 1150.9521,
+      "train_samples_per_second": 0.869,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "max_steps": 15,
+  "num_train_epochs": 5,
+  "total_flos": 4296337784832.0,
+  "trial_name": null,
+  "trial_params": null
+}