Duplicate from vinluvie/clip-general

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,57 @@
+---
+base_model: openai/clip-vit-large-patch14
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: clip-general
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# clip-general
+
+This model is a fine-tuned version of [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1725
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 1.13.1
+- Datasets 2.16.1
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 9.99,
+    "eval_loss": 0.17247404158115387,
+    "eval_runtime": 28.5959,
+    "eval_samples_per_second": 55.742,
+    "eval_steps_per_second": 6.994,
+    "test_loss": 0.19798412919044495,
+    "test_runtime": 32.262,
+    "test_samples_per_second": 49.408,
+    "test_steps_per_second": 6.199,
+    "train_loss": 0.1851580994469779,
+    "train_runtime": 8550.1342,
+    "train_samples_per_second": 16.769,
+    "train_steps_per_second": 0.524
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "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": "4.39.0.dev0",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 9.99,
+    "eval_loss": 0.17247404158115387,
+    "eval_runtime": 28.5959,
+    "eval_samples_per_second": 55.742,
+    "eval_steps_per_second": 6.994
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adb2720bc4e992d1ade7e4970bc2126f28cfbd81a5bf44e60bd1660ab8cae3e8
+size 1710537716

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": 224,
+    "width": 224
+  },
+  "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": 224
+  }
+}

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
+  }
+}

test_results.json

@@ -0,0 +1,6 @@
+{
+    "test_loss": 0.19798412919044495,
+    "test_runtime": 32.262,
+    "test_samples_per_second": 49.408,
+    "test_steps_per_second": 6.199
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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|>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 9.99,
+    "train_loss": 0.1851580994469779,
+    "train_runtime": 8550.1342,
+    "train_samples_per_second": 16.769,
+    "train_steps_per_second": 0.524
+}

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.99442275515895,
+  "eval_steps": 500,
+  "global_step": 4480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.12,
+      "grad_norm": 18.684795379638672,
+      "learning_rate": 4.4419642857142854e-05,
+      "loss": 0.6311,
+      "step": 500
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 13.164822578430176,
+      "learning_rate": 3.883928571428572e-05,
+      "loss": 0.3308,
+      "step": 1000
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 17.804838180541992,
+      "learning_rate": 3.325892857142857e-05,
+      "loss": 0.209,
+      "step": 1500
+    },
+    {
+      "epoch": 4.46,
+      "grad_norm": 4.987255096435547,
+      "learning_rate": 2.767857142857143e-05,
+      "loss": 0.1576,
+      "step": 2000
+    },
+    {
+      "epoch": 5.58,
+      "grad_norm": 9.00122356414795,
+      "learning_rate": 2.2098214285714286e-05,
+      "loss": 0.1173,
+      "step": 2500
+    },
+    {
+      "epoch": 6.69,
+      "grad_norm": 1.4200397729873657,
+      "learning_rate": 1.6517857142857144e-05,
+      "loss": 0.082,
+      "step": 3000
+    },
+    {
+      "epoch": 7.81,
+      "grad_norm": 2.2957751750946045,
+      "learning_rate": 1.09375e-05,
+      "loss": 0.061,
+      "step": 3500
+    },
+    {
+      "epoch": 8.92,
+      "grad_norm": 0.13178028166294098,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.0428,
+      "step": 4000
+    },
+    {
+      "epoch": 9.99,
+      "step": 4480,
+      "total_flos": 2.577776514283278e+16,
+      "train_loss": 0.1851580994469779,
+      "train_runtime": 8550.1342,
+      "train_samples_per_second": 16.769,
+      "train_steps_per_second": 0.524
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2.577776514283278e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa567b402873165d4b6a358749a3c168e00f1402c0e1adad85f7892aef31622
+size 4411