End of training

README.md

@@ -0,0 +1,84 @@
+---
+license: mit
+base_model: microsoft/xclip-base-patch32
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: xclip-base-patch32-finetuned-custom-subset
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/huangyangyu/huggingface/runs/v8zohmjq)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/huangyangyu/huggingface/runs/v8zohmjq)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/huangyangyu/huggingface/runs/v8zohmjq)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/huangyangyu/huggingface/runs/v8zohmjq)
+# xclip-base-patch32-finetuned-custom-subset
+
+This model is a fine-tuned version of [microsoft/xclip-base-patch32](https://huggingface.co/microsoft/xclip-base-patch32) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5862
+- Accuracy: 0.7308
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 1420
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 0.8431        | 0.0507  | 72   | 0.5928          | 0.7308   |
+| 0.6657        | 1.0507  | 144  | 0.7383          | 0.7308   |
+| 0.8019        | 2.0507  | 216  | 0.6047          | 0.7308   |
+| 0.6275        | 3.0507  | 288  | 0.5946          | 0.7308   |
+| 0.561         | 4.0507  | 360  | 0.6646          | 0.7308   |
+| 0.594         | 5.0507  | 432  | 0.6098          | 0.7308   |
+| 0.6472        | 6.0507  | 504  | 0.5915          | 0.7308   |
+| 0.623         | 7.0507  | 576  | 0.5948          | 0.7308   |
+| 0.5711        | 8.0507  | 648  | 0.6056          | 0.7308   |
+| 0.5967        | 9.0507  | 720  | 0.5887          | 0.7308   |
+| 0.5831        | 10.0507 | 792  | 0.5860          | 0.7308   |
+| 0.6101        | 11.0507 | 864  | 0.6044          | 0.7308   |
+| 0.6265        | 12.0507 | 936  | 0.5856          | 0.7308   |
+| 0.6373        | 13.0507 | 1008 | 0.5882          | 0.7308   |
+| 0.665         | 14.0507 | 1080 | 0.5852          | 0.7308   |
+| 0.6183        | 15.0507 | 1152 | 0.5837          | 0.7308   |
+| 0.7786        | 16.0507 | 1224 | 0.5834          | 0.7308   |
+| 0.5489        | 17.0507 | 1296 | 0.5849          | 0.7308   |
+| 0.6512        | 18.0507 | 1368 | 0.5843          | 0.7308   |
+| 0.5266        | 19.0366 | 1420 | 0.5862          | 0.7308   |
+
+
+### Framework versions
+
+- Transformers 4.42.0.dev0
+- Pytorch 2.1.1
+- Datasets 2.13.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,205 @@
+{
+  "_name_or_path": "microsoft/xclip-base-patch32",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 384,
+  "decoder_intermediate_size": 1536,
+  "decoder_num_attention_heads": 6,
+  "decoder_num_hidden_layers": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1"
+  },
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "videomae",
+  "norm_pix_loss": true,
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 16,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "projection_dim": 512,
+  "prompt_alpha": 0.1,
+  "prompt_attention_dropout": 0.0,
+  "prompt_hidden_act": "quick_gelu",
+  "prompt_layers": 2,
+  "prompt_num_attention_heads": 8,
+  "prompt_projection_dropout": 0.0,
+  "qkv_bias": true,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 512,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "xclip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.22.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "tubelet_size": 2,
+  "use_mean_pooling": true,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mit_hidden_size": 512,
+    "mit_intermediate_size": 2048,
+    "mit_num_attention_heads": 8,
+    "mit_num_hidden_layers": 1,
+    "model_type": "xclip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_frames": 8,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 32,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.22.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71904266c5ebe7437fb414d8f957301a2a68c3de64f09af550aac66a42644ed0
+size 344937328

preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "_valid_processor_keys": [
+    "videos",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "VideoMAEImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "processor_class": "XCLIPProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

runs/Jun05_19-15-46_USER-20231127DF/events.out.tfevents.1717586155.USER-20231127DF.4964.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804c8ac3e1a74043fea4c159079d6752ab3bc3f12810b843a9b502fccf80435d
+size 46431

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5399254405706bb59df526cd9390ef86e6ea25cb14d790d5800e64e3f9c82c
+size 5176