End of training

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 8.0,
+    "train_loss": 1.4494519168383455,
+    "train_runtime": 7193.8184,
+    "train_samples_per_second": 1.948,
+    "train_steps_per_second": 0.244
+}

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

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 8.0,
+    "train_loss": 1.4494519168383455,
+    "train_runtime": 7193.8184,
+    "train_samples_per_second": 1.948,
+    "train_steps_per_second": 0.244
+}

trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1752,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.28,
+      "learning_rate": 3.573059360730594e-05,
+      "loss": 1.8355,
+      "step": 500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 2.1461187214611872e-05,
+      "loss": 1.503,
+      "step": 1000
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 7.191780821917809e-06,
+      "loss": 1.2109,
+      "step": 1500
+    },
+    {
+      "epoch": 8.0,
+      "step": 1752,
+      "total_flos": 803810618658432.0,
+      "train_loss": 1.4494519168383455,
+      "train_runtime": 7193.8184,
+      "train_samples_per_second": 1.948,
+      "train_steps_per_second": 0.244
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1752,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 803810618658432.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}