first init

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /home/yfliu/data/code/rl_with_clip/cache/model/vicuna-7b-v1.5
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vicuna-7b-v1.5",
+  "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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d850a919a746f5a6b9e0bd50f7552c79800b3a83e339fc7d300248bcccc57f
+size 639692768

clip/all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9,
+    "eval_loss": 0.9871606230735779,
+    "eval_runtime": 78.3792,
+    "eval_samples_per_second": 12.631,
+    "eval_steps_per_second": 0.051,
+    "total_flos": 8.059090729915764e+17,
+    "train_loss": 0.06507109994963398,
+    "train_runtime": 16858.8681,
+    "train_samples_per_second": 9.491,
+    "train_steps_per_second": 0.678
+}

clip/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "../cache/model/clip-vit-large-patch14-336",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12,
+    "projection_dim": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

clip/eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9,
+    "eval_loss": 0.9871606230735779,
+    "eval_runtime": 78.3792,
+    "eval_samples_per_second": 12.631,
+    "eval_steps_per_second": 0.051
+}

clip/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcef3e68ead1045defeb330dcd34ad5d1f47716de003c4048708f265670e7ae5
+size 1711848436

clip/preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

clip/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

clip/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>",
+  "use_fast": true
+}

clip/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "total_flos": 8.059090729915764e+17,
+    "train_loss": 0.06507109994963398,
+    "train_runtime": 16858.8681,
+    "train_samples_per_second": 9.491,
+    "train_steps_per_second": 0.678
+}

clip/trainer_state.json

@@ -0,0 +1,286 @@
+{
+  "best_metric": 0.9871606230735779,
+  "best_model_checkpoint": "../output/clip_finetune_mix_contrastive_0.1_0.1/checkpoint-1143",
+  "epoch": 10.0,
+  "eval_steps": 10.0,
+  "global_step": 11430,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4374453193350831,
+      "grad_norm": 29.616256713867188,
+      "learning_rate": 9.604569420035148e-07,
+      "loss": 0.4374,
+      "step": 500
+    },
+    {
+      "epoch": 0.8748906386701663,
+      "grad_norm": 73.90093994140625,
+      "learning_rate": 9.165202108963093e-07,
+      "loss": 0.2592,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9,
+      "eval_loss": 0.9871606230735779,
+      "eval_runtime": 63.6759,
+      "eval_samples_per_second": 15.547,
+      "eval_steps_per_second": 0.063,
+      "step": 1143
+    },
+    {
+      "epoch": 1.3123359580052494,
+      "grad_norm": 44.70602798461914,
+      "learning_rate": 8.725834797891036e-07,
+      "loss": 0.155,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7497812773403325,
+      "grad_norm": 27.63109588623047,
+      "learning_rate": 8.28646748681898e-07,
+      "loss": 0.1169,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9090909090909091,
+      "eval_loss": 1.0009111166000366,
+      "eval_runtime": 51.9069,
+      "eval_samples_per_second": 19.073,
+      "eval_steps_per_second": 0.077,
+      "step": 2286
+    },
+    {
+      "epoch": 2.1872265966754156,
+      "grad_norm": 12.88677978515625,
+      "learning_rate": 7.847100175746925e-07,
+      "loss": 0.093,
+      "step": 2500
+    },
+    {
+      "epoch": 2.6246719160104988,
+      "grad_norm": 12.44239330291748,
+      "learning_rate": 7.407732864674868e-07,
+      "loss": 0.0533,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9101010101010101,
+      "eval_loss": 1.0933490991592407,
+      "eval_runtime": 50.0747,
+      "eval_samples_per_second": 19.77,
+      "eval_steps_per_second": 0.08,
+      "step": 3429
+    },
+    {
+      "epoch": 3.062117235345582,
+      "grad_norm": 1.8053172826766968,
+      "learning_rate": 6.968365553602812e-07,
+      "loss": 0.0488,
+      "step": 3500
+    },
+    {
+      "epoch": 3.499562554680665,
+      "grad_norm": 9.218230247497559,
+      "learning_rate": 6.528998242530756e-07,
+      "loss": 0.0385,
+      "step": 4000
+    },
+    {
+      "epoch": 3.937007874015748,
+      "grad_norm": 4.457502365112305,
+      "learning_rate": 6.089630931458699e-07,
+      "loss": 0.0395,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9111111111111111,
+      "eval_loss": 1.1654703617095947,
+      "eval_runtime": 64.5794,
+      "eval_samples_per_second": 15.33,
+      "eval_steps_per_second": 0.062,
+      "step": 4572
+    },
+    {
+      "epoch": 4.374453193350831,
+      "grad_norm": 1.6728917360305786,
+      "learning_rate": 5.650263620386643e-07,
+      "loss": 0.0248,
+      "step": 5000
+    },
+    {
+      "epoch": 4.811898512685914,
+      "grad_norm": 0.3894324004650116,
+      "learning_rate": 5.210896309314587e-07,
+      "loss": 0.0246,
+      "step": 5500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9171717171717172,
+      "eval_loss": 1.2322180271148682,
+      "eval_runtime": 53.1272,
+      "eval_samples_per_second": 18.635,
+      "eval_steps_per_second": 0.075,
+      "step": 5715
+    },
+    {
+      "epoch": 5.2493438320209975,
+      "grad_norm": 0.388487309217453,
+      "learning_rate": 4.77152899824253e-07,
+      "loss": 0.0191,
+      "step": 6000
+    },
+    {
+      "epoch": 5.686789151356081,
+      "grad_norm": 1.2540724277496338,
+      "learning_rate": 4.332161687170474e-07,
+      "loss": 0.0212,
+      "step": 6500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9111111111111111,
+      "eval_loss": 1.296130895614624,
+      "eval_runtime": 60.2328,
+      "eval_samples_per_second": 16.436,
+      "eval_steps_per_second": 0.066,
+      "step": 6858
+    },
+    {
+      "epoch": 6.124234470691164,
+      "grad_norm": 5.201016426086426,
+      "learning_rate": 3.8927943760984183e-07,
+      "loss": 0.0225,
+      "step": 7000
+    },
+    {
+      "epoch": 6.561679790026247,
+      "grad_norm": 0.170638769865036,
+      "learning_rate": 3.453427065026362e-07,
+      "loss": 0.0208,
+      "step": 7500
+    },
+    {
+      "epoch": 6.99912510936133,
+      "grad_norm": 1.351289987564087,
+      "learning_rate": 3.0140597539543056e-07,
+      "loss": 0.0152,
+      "step": 8000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9090909090909091,
+      "eval_loss": 1.2485171556472778,
+      "eval_runtime": 57.7422,
+      "eval_samples_per_second": 17.145,
+      "eval_steps_per_second": 0.069,
+      "step": 8001
+    },
+    {
+      "epoch": 7.436570428696413,
+      "grad_norm": 0.5688414573669434,
+      "learning_rate": 2.5746924428822493e-07,
+      "loss": 0.0155,
+      "step": 8500
+    },
+    {
+      "epoch": 7.874015748031496,
+      "grad_norm": 0.3233714699745178,
+      "learning_rate": 2.1353251318101935e-07,
+      "loss": 0.0149,
+      "step": 9000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9121212121212121,
+      "eval_loss": 1.2698818445205688,
+      "eval_runtime": 134.063,
+      "eval_samples_per_second": 7.385,
+      "eval_steps_per_second": 0.03,
+      "step": 9144
+    },
+    {
+      "epoch": 8.31146106736658,
+      "grad_norm": 0.1916019767522812,
+      "learning_rate": 1.695957820738137e-07,
+      "loss": 0.0132,
+      "step": 9500
+    },
+    {
+      "epoch": 8.748906386701663,
+      "grad_norm": 0.15178655087947845,
+      "learning_rate": 1.2565905096660808e-07,
+      "loss": 0.0185,
+      "step": 10000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9090909090909091,
+      "eval_loss": 1.278696894645691,
+      "eval_runtime": 240.0211,
+      "eval_samples_per_second": 4.125,
+      "eval_steps_per_second": 0.017,
+      "step": 10287
+    },
+    {
+      "epoch": 9.186351706036746,
+      "grad_norm": 0.17507989704608917,
+      "learning_rate": 8.172231985940245e-08,
+      "loss": 0.0125,
+      "step": 10500
+    },
+    {
+      "epoch": 9.623797025371829,
+      "grad_norm": 2.5729331970214844,
+      "learning_rate": 3.7785588752196835e-08,
+      "loss": 0.0108,
+      "step": 11000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9090909090909091,
+      "eval_loss": 1.2581349611282349,
+      "eval_runtime": 124.5141,
+      "eval_samples_per_second": 7.951,
+      "eval_steps_per_second": 0.032,
+      "step": 11430
+    },
+    {
+      "epoch": 10.0,
+      "step": 11430,
+      "total_flos": 8.059090729915764e+17,
+      "train_loss": 0.06507109994963398,
+      "train_runtime": 16858.8681,
+      "train_samples_per_second": 9.491,
+      "train_steps_per_second": 0.678
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11430,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.059090729915764e+17,
+  "train_batch_size": 14,
+  "trial_name": null,
+  "trial_params": null
+}

clip/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6819e358f6b3a0f712872f722f37d4b5be2f3210977cec8e83ea4f370d0eef86
+size 5176

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "：vicuna-7b-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "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": "./clip",
+  "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,
+  "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:f338ab56a402a9595cdaa3b1d71c60f2ed8806a0295a97b7f13ea2a68e5dff75
+size 41961648