End of training

README.md

@@ -2,7 +2,7 @@
 tags:
 - generated_from_trainer
 datasets:
-- coco_dataset_script
+- ydshieh/coco_dataset_script
 model-index:
 - name: clip-roberta-finetuned
   results: []
@@ -13,7 +13,9 @@ 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 was trained from scratch on the ydshieh/coco_dataset_script 2017 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6024
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.6024179458618164,
+    "eval_runtime": 220.1844,
+    "eval_samples_per_second": 96.905,
+    "eval_steps_per_second": 0.191,
+    "total_flos": 2.368703361024e+17,
+    "train_loss": 0.30996957313790807,
+    "train_runtime": 15330.9154,
+    "train_samples_per_second": 115.796,
+    "train_steps_per_second": 0.226
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.6024179458618164,
+    "eval_runtime": 220.1844,
+    "eval_samples_per_second": 96.905,
+    "eval_steps_per_second": 0.191
+}

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 +1,51 @@
+{
+  "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": 3.0,
+    "total_flos": 2.368703361024e+17,
+    "train_loss": 0.30996957313790807,
+    "train_runtime": 15330.9154,
+    "train_samples_per_second": 115.796,
+    "train_steps_per_second": 0.226
+}

trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3465,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4329004329004329,
+      "grad_norm": 5.537757873535156,
+      "learning_rate": 4.278499278499279e-05,
+      "loss": 0.7119,
+      "step": 500
+    },
+    {
+      "epoch": 0.8658008658008658,
+      "grad_norm": 4.387680530548096,
+      "learning_rate": 3.556998556998557e-05,
+      "loss": 0.3833,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2987012987012987,
+      "grad_norm": 3.637988328933716,
+      "learning_rate": 2.8354978354978357e-05,
+      "loss": 0.2849,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7316017316017316,
+      "grad_norm": 3.036390781402588,
+      "learning_rate": 2.113997113997114e-05,
+      "loss": 0.2441,
+      "step": 2000
+    },
+    {
+      "epoch": 2.1645021645021645,
+      "grad_norm": 2.361323356628418,
+      "learning_rate": 1.3924963924963927e-05,
+      "loss": 0.2078,
+      "step": 2500
+    },
+    {
+      "epoch": 2.5974025974025974,
+      "grad_norm": 2.214087963104248,
+      "learning_rate": 6.709956709956711e-06,
+      "loss": 0.1685,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "step": 3465,
+      "total_flos": 2.368703361024e+17,
+      "train_loss": 0.30996957313790807,
+      "train_runtime": 15330.9154,
+      "train_samples_per_second": 115.796,
+      "train_steps_per_second": 0.226
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3465,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.368703361024e+17,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}