End of training

README.md

@@ -13,6 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
 # clip-seed-vit-4
 
 This model is a fine-tuned version of [openai/clip-vit-base-patch16](https://huggingface.co/openai/clip-vit-base-patch16) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2432
 
 ## Model description
 

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 2.2431678771972656,
+    "eval_runtime": 41.3085,
+    "eval_samples_per_second": 6.391,
+    "eval_steps_per_second": 0.799,
+    "train_loss": 1.9904336006410661,
+    "train_runtime": 3213.5193,
+    "train_samples_per_second": 1.852,
+    "train_steps_per_second": 0.232
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 2.2431678771972656,
+    "eval_runtime": 41.3085,
+    "eval_samples_per_second": 6.391,
+    "eval_steps_per_second": 0.799
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "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
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 1.9904336006410661,
+    "train_runtime": 3213.5193,
+    "train_samples_per_second": 1.852,
+    "train_steps_per_second": 0.232
+}

trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 744,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.639784946236559e-05,
+      "loss": 2.0688,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "step": 744,
+      "total_flos": 341344235320704.0,
+      "train_loss": 1.9904336006410661,
+      "train_runtime": 3213.5193,
+      "train_samples_per_second": 1.852,
+      "train_steps_per_second": 0.232
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 744,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 341344235320704.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}