End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 60.0,
+    "eval_accuracy": 0.06694191635136518,
+    "eval_loss": 3.553868532180786,
+    "eval_runtime": 50.3598,
+    "eval_samples_per_second": 141.224,
+    "eval_steps_per_second": 7.069,
+    "total_flos": 2.541067006369997e+18,
+    "train_loss": 1.3772225892310048,
+    "train_runtime": 58902.9646,
+    "train_samples_per_second": 54.543,
+    "train_steps_per_second": 0.26
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 60.0,
+    "eval_accuracy": 0.06694191635136518,
+    "eval_loss": 3.553868532180786,
+    "eval_runtime": 50.3598,
+    "eval_samples_per_second": 141.224,
+    "eval_steps_per_second": 7.069
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "ChineseCLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 60.0,
+    "total_flos": 2.541067006369997e+18,
+    "train_loss": 1.3772225892310048,
+    "train_runtime": 58902.9646,
+    "train_samples_per_second": 54.543,
+    "train_steps_per_second": 0.26
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 60.0,
+  "eval_steps": 1530,
+  "global_step": 15300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.6894794702529907,
+      "learning_rate": 9.000653594771243e-06,
+      "loss": 1.5814,
+      "step": 1530
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.07255343082114736,
+      "eval_loss": 3.025679588317871,
+      "eval_runtime": 50.7219,
+      "eval_samples_per_second": 140.216,
+      "eval_steps_per_second": 7.019,
+      "step": 1530
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 5.62229061126709,
+      "learning_rate": 8.001307189542484e-06,
+      "loss": 1.4807,
+      "step": 3060
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.07121766029246344,
+      "eval_loss": 3.267681121826172,
+      "eval_runtime": 50.6404,
+      "eval_samples_per_second": 140.441,
+      "eval_steps_per_second": 7.03,
+      "step": 3060
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 1.747545599937439,
+      "learning_rate": 7.001960784313726e-06,
+      "loss": 1.4075,
+      "step": 4590
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.07025684289463817,
+      "eval_loss": 3.333199977874756,
+      "eval_runtime": 50.6734,
+      "eval_samples_per_second": 140.35,
+      "eval_steps_per_second": 7.025,
+      "step": 4590
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 3.056417465209961,
+      "learning_rate": 6.002614379084968e-06,
+      "loss": 1.3618,
+      "step": 6120
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.06924915635545557,
+      "eval_loss": 3.249127149581909,
+      "eval_runtime": 50.8822,
+      "eval_samples_per_second": 139.774,
+      "eval_steps_per_second": 6.997,
+      "step": 6120
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 5.729462146759033,
+      "learning_rate": 5.002614379084968e-06,
+      "loss": 1.3396,
+      "step": 7650
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.06903824521934758,
+      "eval_loss": 3.3755784034729004,
+      "eval_runtime": 50.6692,
+      "eval_samples_per_second": 140.361,
+      "eval_steps_per_second": 7.026,
+      "step": 7650
+    },
+    {
+      "epoch": 36.0,
+      "grad_norm": 3.0638558864593506,
+      "learning_rate": 4.00326797385621e-06,
+      "loss": 1.3298,
+      "step": 9180
+    },
+    {
+      "epoch": 36.0,
+      "eval_accuracy": 0.06781964754405699,
+      "eval_loss": 3.5385994911193848,
+      "eval_runtime": 50.6377,
+      "eval_samples_per_second": 140.449,
+      "eval_steps_per_second": 7.03,
+      "step": 9180
+    },
+    {
+      "epoch": 42.0,
+      "grad_norm": 1.3296822309494019,
+      "learning_rate": 3.0039215686274516e-06,
+      "loss": 1.324,
+      "step": 10710
+    },
+    {
+      "epoch": 42.0,
+      "eval_accuracy": 0.06745139000482082,
+      "eval_loss": 3.524540901184082,
+      "eval_runtime": 50.7535,
+      "eval_samples_per_second": 140.128,
+      "eval_steps_per_second": 7.014,
+      "step": 10710
+    },
+    {
+      "epoch": 48.0,
+      "grad_norm": 0.8740301132202148,
+      "learning_rate": 2.004575163398693e-06,
+      "loss": 1.3177,
+      "step": 12240
+    },
+    {
+      "epoch": 48.0,
+      "eval_accuracy": 0.06706974128233971,
+      "eval_loss": 3.513636827468872,
+      "eval_runtime": 50.7526,
+      "eval_samples_per_second": 140.131,
+      "eval_steps_per_second": 7.014,
+      "step": 12240
+    },
+    {
+      "epoch": 54.0,
+      "grad_norm": 0.6789987683296204,
+      "learning_rate": 1.004575163398693e-06,
+      "loss": 1.3181,
+      "step": 13770
+    },
+    {
+      "epoch": 54.0,
+      "eval_accuracy": 0.0669135108111486,
+      "eval_loss": 3.4984188079833984,
+      "eval_runtime": 50.596,
+      "eval_samples_per_second": 140.564,
+      "eval_steps_per_second": 7.036,
+      "step": 13770
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 0.4347877502441406,
+      "learning_rate": 5.2287581699346415e-09,
+      "loss": 1.3117,
+      "step": 15300
+    },
+    {
+      "epoch": 60.0,
+      "eval_accuracy": 0.06692913385826772,
+      "eval_loss": 3.553868532180786,
+      "eval_runtime": 50.6817,
+      "eval_samples_per_second": 140.327,
+      "eval_steps_per_second": 7.024,
+      "step": 15300
+    },
+    {
+      "epoch": 60.0,
+      "step": 15300,
+      "total_flos": 2.541067006369997e+18,
+      "train_loss": 1.3772225892310048,
+      "train_runtime": 58902.9646,
+      "train_samples_per_second": 54.543,
+      "train_steps_per_second": 0.26
+    }
+  ],
+  "logging_steps": 1530,
+  "max_steps": 15300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 60,
+  "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": 2.541067006369997e+18,
+  "train_batch_size": 15,
+  "trial_name": null,
+  "trial_params": null
+}