Model save

README.md

@@ -0,0 +1,57 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: clip-roberta-finetuned
+  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/ahmedchtourou2019/huggingface/runs/3nvkg166)
+# clip-roberta-finetuned
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7544
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.0141        | 1.0   | 1    | 1.6837          |
+| 4.1484        | 2.0   | 2    | 1.7544          |
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 3.893137216567993,
+    "eval_runtime": 22.5319,
+    "eval_samples_per_second": 6.657,
+    "eval_steps_per_second": 0.133,
+    "total_flos": 266767525440000.0,
+    "train_loss": 4.029143333435059,
+    "train_runtime": 1253.0431,
+    "train_samples_per_second": 1.595,
+    "train_steps_per_second": 0.026
+}

config.json

@@ -0,0 +1,168 @@
+{
+  "_name_or_path": "./clip-roberta",
+  "architectures": [
+    "VisionTextDualEncoderModel"
+  ],
+  "logit_scale_init_value": 2.6592,
+  "model_type": "vision-text-dual-encoder",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "FacebookAI/roberta-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "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": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "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,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "roberta",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "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,
+    "position_embedding_type": "absolute",
+    "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,
+    "suppress_tokens": 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,
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "vision_config": {
+    "_name_or_path": "openai/clip-vit-base-patch32",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": 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,
+    "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,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "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,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": 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,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 3.893137216567993,
+    "eval_runtime": 22.5319,
+    "eval_samples_per_second": 6.657,
+    "eval_steps_per_second": 0.133
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0ebbb17fb374fae361481a680b79025b82eb5ee94c53d54d073230224800f4
+size 851603588

preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "_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
+  ],
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

runs/Apr23_14-40-22_87b1853ebd42/events.out.tfevents.1713883848.87b1853ebd42.3330.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2494cf2d64d21827ff711044fe3759abfa8c46941dd2dd2fa7b8b1bd9b0d4d
+size 8996

runs/Apr23_14-40-22_87b1853ebd42/events.out.tfevents.1713884578.87b1853ebd42.3330.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793658b5b5d4594ec526456dc91c37cb8d2871742fc12e6965698b2ef76cf5ac
+size 354

runs/Apr24_14-17-17_4d9e3066714e/events.out.tfevents.1713968742.4d9e3066714e.2953.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b51f2f6bc88803030833400f2a1599001a68d724678f51913b74d997f2bf047
+size 38793

runs/Apr24_14-17-17_4d9e3066714e/events.out.tfevents.1713970006.4d9e3066714e.2953.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ec20676a89d242f2fcd9331a586da26ceaf263687428217da54be3eea20903
+size 354

runs/Apr24_20-57-27_a73a230dd558/events.out.tfevents.1713992256.a73a230dd558.12284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41270281a2b21fe5d9151ba193437a21ae3c9cc373389b2ab272a0f58a7b5f9c
+size 17493

runs/Apr24_20-57-27_a73a230dd558/events.out.tfevents.1713993703.a73a230dd558.12284.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39eee467960c4a5f9817accbc3f4e8e9fd5e1dad7b9ca66a2f7bb2707481fa19
+size 354

runs/Apr25_16-44-45_e00da5affe68/events.out.tfevents.1714064392.e00da5affe68.1696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da646197cc6225afb1b1f5ffbf12c604682a98335bb3343dc0c58b5be72988fd
+size 8745

runs/May06_10-39-50_b0cf0c1defaa/events.out.tfevents.1714992000.b0cf0c1defaa.11656.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330c472929a65aef85c3767fe701044f10ab50fe3e236b158401b87bc0173388
+size 10039

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 266767525440000.0,
+    "train_loss": 4.029143333435059,
+    "train_runtime": 1253.0431,
+    "train_samples_per_second": 1.595,
+    "train_steps_per_second": 0.026
+}

trainer_state.json

@@ -0,0 +1,286 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 1.0,
+  "global_step": 32,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0625,
+      "eval_loss": 4.102813243865967,
+      "eval_runtime": 46.3336,
+      "eval_samples_per_second": 3.237,
+      "eval_steps_per_second": 0.065,
+      "step": 1
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 4.02440071105957,
+      "eval_runtime": 8.6463,
+      "eval_samples_per_second": 17.348,
+      "eval_steps_per_second": 0.347,
+      "step": 2
+    },
+    {
+      "epoch": 0.1875,
+      "eval_loss": 4.143311500549316,
+      "eval_runtime": 16.1378,
+      "eval_samples_per_second": 9.295,
+      "eval_steps_per_second": 0.186,
+      "step": 3
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 4.173377990722656,
+      "eval_runtime": 8.329,
+      "eval_samples_per_second": 18.009,
+      "eval_steps_per_second": 0.36,
+      "step": 4
+    },
+    {
+      "epoch": 0.3125,
+      "eval_loss": 4.01168155670166,
+      "eval_runtime": 16.236,
+      "eval_samples_per_second": 9.239,
+      "eval_steps_per_second": 0.185,
+      "step": 5
+    },
+    {
+      "epoch": 0.375,
+      "eval_loss": 4.010961055755615,
+      "eval_runtime": 8.3188,
+      "eval_samples_per_second": 18.031,
+      "eval_steps_per_second": 0.361,
+      "step": 6
+    },
+    {
+      "epoch": 0.4375,
+      "eval_loss": 4.041440486907959,
+      "eval_runtime": 15.8046,
+      "eval_samples_per_second": 9.491,
+      "eval_steps_per_second": 0.19,
+      "step": 7
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 4.010050296783447,
+      "eval_runtime": 8.7811,
+      "eval_samples_per_second": 17.082,
+      "eval_steps_per_second": 0.342,
+      "step": 8
+    },
+    {
+      "epoch": 0.5625,
+      "eval_loss": 4.008200645446777,
+      "eval_runtime": 15.9749,
+      "eval_samples_per_second": 9.39,
+      "eval_steps_per_second": 0.188,
+      "step": 9
+    },
+    {
+      "epoch": 0.625,
+      "eval_loss": 3.9981045722961426,
+      "eval_runtime": 8.2704,
+      "eval_samples_per_second": 18.137,
+      "eval_steps_per_second": 0.363,
+      "step": 10
+    },
+    {
+      "epoch": 0.6875,
+      "eval_loss": 3.9941446781158447,
+      "eval_runtime": 15.9208,
+      "eval_samples_per_second": 9.422,
+      "eval_steps_per_second": 0.188,
+      "step": 11
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 3.995903253555298,
+      "eval_runtime": 8.2167,
+      "eval_samples_per_second": 18.255,
+      "eval_steps_per_second": 0.365,
+      "step": 12
+    },
+    {
+      "epoch": 0.8125,
+      "eval_loss": 3.9886744022369385,
+      "eval_runtime": 15.9708,
+      "eval_samples_per_second": 9.392,
+      "eval_steps_per_second": 0.188,
+      "step": 13
+    },
+    {
+      "epoch": 0.875,
+      "eval_loss": 3.982693672180176,
+      "eval_runtime": 8.8265,
+      "eval_samples_per_second": 16.994,
+      "eval_steps_per_second": 0.34,
+      "step": 14
+    },
+    {
+      "epoch": 0.9375,
+      "eval_loss": 3.9799349308013916,
+      "eval_runtime": 15.9139,
+      "eval_samples_per_second": 9.426,
+      "eval_steps_per_second": 0.189,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.9809114933013916,
+      "eval_runtime": 2.7645,
+      "eval_samples_per_second": 54.259,
+      "eval_steps_per_second": 1.085,
+      "step": 16
+    },
+    {
+      "epoch": 1.0625,
+      "eval_loss": 3.9646639823913574,
+      "eval_runtime": 8.3504,
+      "eval_samples_per_second": 17.963,
+      "eval_steps_per_second": 0.359,
+      "step": 17
+    },
+    {
+      "epoch": 1.125,
+      "eval_loss": 3.9485819339752197,
+      "eval_runtime": 2.9291,
+      "eval_samples_per_second": 51.21,
+      "eval_steps_per_second": 1.024,
+      "step": 18
+    },
+    {
+      "epoch": 1.1875,
+      "eval_loss": 3.9438858032226562,
+      "eval_runtime": 15.8414,
+      "eval_samples_per_second": 9.469,
+      "eval_steps_per_second": 0.189,
+      "step": 19
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 3.941105842590332,
+      "eval_runtime": 2.7691,
+      "eval_samples_per_second": 54.17,
+      "eval_steps_per_second": 1.083,
+      "step": 20
+    },
+    {
+      "epoch": 1.3125,
+      "eval_loss": 3.933875322341919,
+      "eval_runtime": 8.7798,
+      "eval_samples_per_second": 17.085,
+      "eval_steps_per_second": 0.342,
+      "step": 21
+    },
+    {
+      "epoch": 1.375,
+      "eval_loss": 3.9402499198913574,
+      "eval_runtime": 3.0846,
+      "eval_samples_per_second": 48.629,
+      "eval_steps_per_second": 0.973,
+      "step": 22
+    },
+    {
+      "epoch": 1.4375,
+      "eval_loss": 3.964958429336548,
+      "eval_runtime": 16.1126,
+      "eval_samples_per_second": 9.31,
+      "eval_steps_per_second": 0.186,
+      "step": 23
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 3.963437080383301,
+      "eval_runtime": 2.8397,
+      "eval_samples_per_second": 52.822,
+      "eval_steps_per_second": 1.056,
+      "step": 24
+    },
+    {
+      "epoch": 1.5625,
+      "eval_loss": 3.9432413578033447,
+      "eval_runtime": 8.5666,
+      "eval_samples_per_second": 17.51,
+      "eval_steps_per_second": 0.35,
+      "step": 25
+    },
+    {
+      "epoch": 1.625,
+      "eval_loss": 3.9292993545532227,
+      "eval_runtime": 2.8879,
+      "eval_samples_per_second": 51.94,
+      "eval_steps_per_second": 1.039,
+      "step": 26
+    },
+    {
+      "epoch": 1.6875,
+      "eval_loss": 3.916614532470703,
+      "eval_runtime": 16.1071,
+      "eval_samples_per_second": 9.313,
+      "eval_steps_per_second": 0.186,
+      "step": 27
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 3.9063076972961426,
+      "eval_runtime": 2.884,
+      "eval_samples_per_second": 52.01,
+      "eval_steps_per_second": 1.04,
+      "step": 28
+    },
+    {
+      "epoch": 1.8125,
+      "eval_loss": 3.9020252227783203,
+      "eval_runtime": 8.445,
+      "eval_samples_per_second": 17.762,
+      "eval_steps_per_second": 0.355,
+      "step": 29
+    },
+    {
+      "epoch": 1.875,
+      "eval_loss": 3.8990707397460938,
+      "eval_runtime": 3.0029,
+      "eval_samples_per_second": 49.952,
+      "eval_steps_per_second": 0.999,
+      "step": 30
+    },
+    {
+      "epoch": 1.9375,
+      "eval_loss": 3.8950419425964355,
+      "eval_runtime": 16.0252,
+      "eval_samples_per_second": 9.36,
+      "eval_steps_per_second": 0.187,
+      "step": 31
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.893137216567993,
+      "eval_runtime": 2.8946,
+      "eval_samples_per_second": 51.821,
+      "eval_steps_per_second": 1.036,
+      "step": 32
+    },
+    {
+      "epoch": 2.0,
+      "step": 32,
+      "total_flos": 266767525440000.0,
+      "train_loss": 4.029143333435059,
+      "train_runtime": 1253.0431,
+      "train_samples_per_second": 1.595,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 32,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 266767525440000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2fe482bbe8d183d739c92755f0d99020a7c9af4003925ae1d9f71d59774596
+size 5112