End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # clip_finetune_0207
 
 This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3411
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.34109967947006226,
+    "eval_runtime": 382.2208,
+    "eval_samples_per_second": 15.219,
+    "eval_steps_per_second": 1.905,
+    "total_flos": 3.031314932000124e+16,
+    "train_loss": 0.4382253171182146,
+    "train_runtime": 35381.4579,
+    "train_samples_per_second": 14.729,
+    "train_steps_per_second": 0.058
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.34109967947006226,
+    "eval_runtime": 382.2208,
+    "eval_samples_per_second": 15.219,
+    "eval_steps_per_second": 1.905
+}

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": 10.0,
+    "total_flos": 3.031314932000124e+16,
+    "train_loss": 0.4382253171182146,
+    "train_runtime": 35381.4579,
+    "train_samples_per_second": 14.729,
+    "train_steps_per_second": 0.058
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500.0,
+  "global_step": 2040,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 32.19416046142578,
+      "learning_rate": 1.5e-05,
+      "loss": 1.0988,
+      "step": 500
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 32.49726867675781,
+      "learning_rate": 3e-05,
+      "loss": 0.4341,
+      "step": 1000
+    },
+    {
+      "epoch": 7.352941176470588,
+      "grad_norm": 9.985998153686523,
+      "learning_rate": 1.557692307692308e-05,
+      "loss": 0.2037,
+      "step": 1500
+    },
+    {
+      "epoch": 9.803921568627452,
+      "grad_norm": 7.020397663116455,
+      "learning_rate": 1.153846153846154e-06,
+      "loss": 0.0495,
+      "step": 2000
+    },
+    {
+      "epoch": 10.0,
+      "step": 2040,
+      "total_flos": 3.031314932000124e+16,
+      "train_loss": 0.4382253171182146,
+      "train_runtime": 35381.4579,
+      "train_samples_per_second": 14.729,
+      "train_steps_per_second": 0.058
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2040,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.031314932000124e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}