End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # CLIP_ViT_L_14_PCSP5
 
 This model is a fine-tuned version of [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0111
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 500.0,
+    "eval_loss": 0.011138472706079483,
+    "eval_runtime": 1.0009,
+    "eval_samples_per_second": 60.945,
+    "eval_steps_per_second": 3.996,
+    "total_flos": 2.176538025123e+16,
+    "train_loss": 0.18364764293190092,
+    "train_runtime": 2711.45,
+    "train_samples_per_second": 44.626,
+    "train_steps_per_second": 1.475
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 500.0,
+    "eval_loss": 0.011138472706079483,
+    "eval_runtime": 1.0009,
+    "eval_samples_per_second": 60.945,
+    "eval_steps_per_second": 3.996
+}

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 +1,31 @@
+{
+  "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": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 500.0,
+    "total_flos": 2.176538025123e+16,
+    "train_loss": 0.18364764293190092,
+    "train_runtime": 2711.45,
+    "train_samples_per_second": 44.626,
+    "train_steps_per_second": 1.475
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 500.0,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 62.5,
+      "grad_norm": 9.630138397216797,
+      "learning_rate": 4.375e-05,
+      "loss": 0.8624,
+      "step": 500
+    },
+    {
+      "epoch": 125.0,
+      "grad_norm": 1.9023737907409668,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.2825,
+      "step": 1000
+    },
+    {
+      "epoch": 187.5,
+      "grad_norm": 4.60806941986084,
+      "learning_rate": 3.125e-05,
+      "loss": 0.1628,
+      "step": 1500
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 0.7057669758796692,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0998,
+      "step": 2000
+    },
+    {
+      "epoch": 312.5,
+      "grad_norm": 9.289773941040039,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.0489,
+      "step": 2500
+    },
+    {
+      "epoch": 375.0,
+      "grad_norm": 0.0008892796467989683,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0117,
+      "step": 3000
+    },
+    {
+      "epoch": 437.5,
+      "grad_norm": 0.008542646653950214,
+      "learning_rate": 6.25e-06,
+      "loss": 0.001,
+      "step": 3500
+    },
+    {
+      "epoch": 500.0,
+      "grad_norm": 3.78551339963451e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "step": 4000
+    },
+    {
+      "epoch": 500.0,
+      "step": 4000,
+      "total_flos": 2.176538025123e+16,
+      "train_loss": 0.18364764293190092,
+      "train_runtime": 2711.45,
+      "train_samples_per_second": 44.626,
+      "train_steps_per_second": 1.475
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 500,
+  "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": 2.176538025123e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}