End of training

README.md

@@ -1,8 +1,9 @@
 ---
+base_model: ./clip-roberta
 tags:
 - generated_from_trainer
 datasets:
-- coco_dataset_script
+- ydshieh/coco_dataset_script
 model-index:
 - name: clip-roberta-finetuned
   results: []
@@ -13,7 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # clip-roberta-finetuned
 
-This model was trained from scratch on the coco_dataset_script dataset.
+This model is a fine-tuned version of [./clip-roberta](https://huggingface.co/./clip-roberta) on the ydshieh/coco_dataset_script 2017 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6224
 
 ## Model description
 

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.622399926185608,
+    "eval_runtime": 499.7766,
+    "eval_samples_per_second": 50.05,
+    "eval_steps_per_second": 0.782,
+    "train_loss": 0.5455552286053394,
+    "train_runtime": 25986.0373,
+    "train_samples_per_second": 22.772,
+    "train_steps_per_second": 0.356
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.622399926185608,
+    "eval_runtime": 499.7766,
+    "eval_samples_per_second": 50.05,
+    "eval_steps_per_second": 0.782
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "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
+  }
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "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 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.5455552286053394,
+    "train_runtime": 25986.0373,
+    "train_samples_per_second": 22.772,
+    "train_steps_per_second": 0.356
+}

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 9247,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.7296420460689956e-05,
+      "loss": 1.3402,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.459284092137991e-05,
+      "loss": 0.9119,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.188926138206986e-05,
+      "loss": 0.8126,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.9185681842759816e-05,
+      "loss": 0.7416,
+      "step": 2000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.648210230344977e-05,
+      "loss": 0.6728,
+      "step": 2500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.3778522764139723e-05,
+      "loss": 0.6253,
+      "step": 3000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.107494322482968e-05,
+      "loss": 0.569,
+      "step": 3500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.837136368551963e-05,
+      "loss": 0.5355,
+      "step": 4000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.5667784146209584e-05,
+      "loss": 0.4955,
+      "step": 4500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.2964204606899537e-05,
+      "loss": 0.4613,
+      "step": 5000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.026062506758949e-05,
+      "loss": 0.4306,
+      "step": 5500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.755704552827944e-05,
+      "loss": 0.4053,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.4853465988969395e-05,
+      "loss": 0.3821,
+      "step": 6500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.214988644965935e-05,
+      "loss": 0.3572,
+      "step": 7000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.446306910349303e-06,
+      "loss": 0.3274,
+      "step": 7500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.742727371039257e-06,
+      "loss": 0.3131,
+      "step": 8000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.03914783172921e-06,
+      "loss": 0.2879,
+      "step": 8500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.335568292419163e-06,
+      "loss": 0.2808,
+      "step": 9000
+    },
+    {
+      "epoch": 1.0,
+      "step": 9247,
+      "total_flos": 7.900925099184e+16,
+      "train_loss": 0.5455552286053394,
+      "train_runtime": 25986.0373,
+      "train_samples_per_second": 22.772,
+      "train_steps_per_second": 0.356
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9247,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 7.900925099184e+16,
+  "trial_name": null,
+  "trial_params": null
+}