End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # category_cleaning_imagefolder
 
 This model was trained from scratch on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7548
 
 ## Model description
 

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.754795551300049,
+    "eval_runtime": 34.2035,
+    "eval_samples_per_second": 122.21,
+    "eval_steps_per_second": 1.93,
+    "train_loss": 2.0960015277473296,
+    "train_runtime": 1329.2473,
+    "train_samples_per_second": 56.601,
+    "train_steps_per_second": 0.885
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.754795551300049,
+    "eval_runtime": 34.2035,
+    "eval_samples_per_second": 122.21,
+    "eval_steps_per_second": 1.93
+}

preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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
+  }
+}

runs/Mar11_13-14-28_2ba8b42aa987/events.out.tfevents.1710164320.2ba8b42aa987.11181.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14394945a3e29ef0cb1d2f5d7d13ab6aec922b4a74df8304371206a22972e775
+size 359

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": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.0960015277473296,
+    "train_runtime": 1329.2473,
+    "train_samples_per_second": 56.601,
+    "train_steps_per_second": 0.885
+}

trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100.0,
+  "global_step": 1176,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26,
+      "grad_norm": 20.62335205078125,
+      "learning_rate": 4.5748299319727895e-05,
+      "loss": 3.0207,
+      "step": 100
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 24.41301155090332,
+      "learning_rate": 4.149659863945579e-05,
+      "loss": 2.8238,
+      "step": 200
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 23.851058959960938,
+      "learning_rate": 3.724489795918368e-05,
+      "loss": 2.7176,
+      "step": 300
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 21.198942184448242,
+      "learning_rate": 3.2993197278911564e-05,
+      "loss": 2.606,
+      "step": 400
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 22.139713287353516,
+      "learning_rate": 2.8741496598639456e-05,
+      "loss": 2.1191,
+      "step": 500
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 26.165542602539062,
+      "learning_rate": 2.448979591836735e-05,
+      "loss": 2.1034,
+      "step": 600
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 30.156545639038086,
+      "learning_rate": 2.023809523809524e-05,
+      "loss": 2.0801,
+      "step": 700
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 16.38189697265625,
+      "learning_rate": 1.5986394557823133e-05,
+      "loss": 1.908,
+      "step": 800
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 21.190061569213867,
+      "learning_rate": 1.1734693877551021e-05,
+      "loss": 1.4389,
+      "step": 900
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 28.82680320739746,
+      "learning_rate": 7.482993197278912e-06,
+      "loss": 1.4339,
+      "step": 1000
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 26.55443572998047,
+      "learning_rate": 3.231292517006803e-06,
+      "loss": 1.3741,
+      "step": 1100
+    },
+    {
+      "epoch": 3.0,
+      "step": 1176,
+      "total_flos": 4376310425967942.0,
+      "train_loss": 2.0960015277473296,
+      "train_runtime": 1329.2473,
+      "train_samples_per_second": 56.601,
+      "train_steps_per_second": 0.885
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1176,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 4376310425967942.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}