initial commit

README.md

@@ -0,0 +1,54 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- ydshieh/coco_dataset_script
+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. -->
+
+# clip-roberta-finetuned
+
+This model is a fine-tuned version of [./models/clip-roberta](https://huggingface.co/./models/clip-roberta) on the ydshieh/coco_dataset_script 2017 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7269
+
+## 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: 256
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.19.2
+- Pytorch 1.11.0+cu113
+- Datasets 1.18.4
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.7268519401550293,
+    "eval_runtime": 1402.9095,
+    "eval_samples_per_second": 17.7,
+    "eval_steps_per_second": 0.069,
+    "train_loss": 1.5387164243717784,
+    "train_runtime": 5043.8105,
+    "train_samples_per_second": 14.638,
+    "train_steps_per_second": 0.058
+}

config.json

@@ -0,0 +1,162 @@
+{
+  "_name_or_path": "./models/clip-roberta",
+  "architectures": [
+    "VisionTextDualEncoderModel"
+  ],
+  "logit_scale_init_value": 2.6592,
+  "model_type": "vision-text-dual-encoder",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "adalbertojunior/rpt",
+    "add_cross_attention": false,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": 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,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.19.2",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "openai/clip-vit-base-patch32",
+    "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,
+    "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_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,
+    "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": "4.19.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.7268519401550293,
+    "eval_runtime": 1402.9095,
+    "eval_samples_per_second": 17.7,
+    "eval_steps_per_second": 0.069
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b2be2c521f53c610bf5e7299687862873c1eaef6b38fad9050693cf0d48077
+size 851695707

runs/Jun09_17-05-49_9eca2fda50d1/1654794374.2161763/events.out.tfevents.1654794374.9eca2fda50d1.34053.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b9abdbabd26f94056518438a628865aa979284ba2463ca8de65551d93496ce
+size 5208

runs/Jun09_17-05-49_9eca2fda50d1/events.out.tfevents.1654794374.9eca2fda50d1.34053.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80a1e9682ea74d85f7be074c55860e1af2bc3d191714a2f9fe5d6342b8f4948
+size 7339

runs/Jun09_17-07-29_9eca2fda50d1/1654794463.3412402/events.out.tfevents.1654794463.9eca2fda50d1.34486.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555dcc70d43b70f60be682b57d5656b69bc926899ad951565e215074544385b1
+size 5208

runs/Jun09_17-07-29_9eca2fda50d1/events.out.tfevents.1654794463.9eca2fda50d1.34486.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ba3afda5ca6b335c5995cc8df23fd0977413b9bcf13249ce3c180273c1f5b3
+size 7693

runs/Jun09_17-07-29_9eca2fda50d1/events.out.tfevents.1654800911.9eca2fda50d1.34486.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bb8a6f3d11b75218458f8cc283af6f6ab1d40fc8c30a48b3a79df9fb6d7022
+size 311

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.5387164243717784,
+    "train_runtime": 5043.8105,
+    "train_samples_per_second": 14.638,
+    "train_steps_per_second": 0.058
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 291,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 291,
+      "total_flos": 9857580782400000.0,
+      "train_loss": 1.5387164243717784,
+      "train_runtime": 5043.8105,
+      "train_samples_per_second": 14.638,
+      "train_steps_per_second": 0.058
+    }
+  ],
+  "max_steps": 291,
+  "num_train_epochs": 3,
+  "total_flos": 9857580782400000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c25d2efb4754daaf7fac41aa658c405d1444a3be6a3038531bbc578925dcaf9
+size 3247