End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [OFA-Sys/chinese-clip-vit-base-patch16](https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 4.4601
-- Accuracy: 0.0942
+- Accuracy: 0.0939
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 199.4579945799458,
+    "eval_accuracy": 0.09392712550607288,
+    "eval_loss": 4.4601263999938965,
+    "eval_runtime": 4.4396,
+    "eval_samples_per_second": 278.177,
+    "eval_steps_per_second": 13.965,
+    "total_flos": 7.267108691140301e+17,
+    "train_loss": 0.527852494612984,
+    "train_runtime": 15509.2666,
+    "train_samples_per_second": 118.806,
+    "train_steps_per_second": 0.593
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 199.4579945799458,
+    "eval_accuracy": 0.09392712550607288,
+    "eval_loss": 4.4601263999938965,
+    "eval_runtime": 4.4396,
+    "eval_samples_per_second": 278.177,
+    "eval_steps_per_second": 13.965
+}

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": 199.4579945799458,
+    "total_flos": 7.267108691140301e+17,
+    "train_loss": 0.527852494612984,
+    "train_runtime": 15509.2666,
+    "train_samples_per_second": 118.806,
+    "train_steps_per_second": 0.593
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 199.4579945799458,
+  "eval_steps": 920,
+  "global_step": 9200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 19.94579945799458,
+      "grad_norm": 7.373812198638916,
+      "learning_rate": 9.00217391304348e-06,
+      "loss": 0.8826,
+      "step": 920
+    },
+    {
+      "epoch": 19.94579945799458,
+      "eval_accuracy": 0.10445344129554655,
+      "eval_loss": 3.48262619972229,
+      "eval_runtime": 4.7057,
+      "eval_samples_per_second": 262.45,
+      "eval_steps_per_second": 13.176,
+      "step": 920
+    },
+    {
+      "epoch": 39.89159891598916,
+      "grad_norm": 3.8576836585998535,
+      "learning_rate": 8.002173913043479e-06,
+      "loss": 0.5489,
+      "step": 1840
+    },
+    {
+      "epoch": 39.89159891598916,
+      "eval_accuracy": 0.1048582995951417,
+      "eval_loss": 3.5594887733459473,
+      "eval_runtime": 4.6918,
+      "eval_samples_per_second": 263.227,
+      "eval_steps_per_second": 13.215,
+      "step": 1840
+    },
+    {
+      "epoch": 59.83739837398374,
+      "grad_norm": 2.5869300365448,
+      "learning_rate": 7.002173913043478e-06,
+      "loss": 0.5099,
+      "step": 2760
+    },
+    {
+      "epoch": 59.83739837398374,
+      "eval_accuracy": 0.10067476383265857,
+      "eval_loss": 3.674304246902466,
+      "eval_runtime": 4.7105,
+      "eval_samples_per_second": 262.181,
+      "eval_steps_per_second": 13.162,
+      "step": 2760
+    },
+    {
+      "epoch": 79.78319783197831,
+      "grad_norm": 1.2137285470962524,
+      "learning_rate": 6.003260869565218e-06,
+      "loss": 0.4939,
+      "step": 3680
+    },
+    {
+      "epoch": 79.78319783197831,
+      "eval_accuracy": 0.10040485829959514,
+      "eval_loss": 3.7631378173828125,
+      "eval_runtime": 4.6611,
+      "eval_samples_per_second": 264.96,
+      "eval_steps_per_second": 13.302,
+      "step": 3680
+    },
+    {
+      "epoch": 99.7289972899729,
+      "grad_norm": 1.5693753957748413,
+      "learning_rate": 5.003260869565218e-06,
+      "loss": 0.4833,
+      "step": 4600
+    },
+    {
+      "epoch": 99.7289972899729,
+      "eval_accuracy": 0.09878542510121457,
+      "eval_loss": 4.000339031219482,
+      "eval_runtime": 4.6602,
+      "eval_samples_per_second": 265.008,
+      "eval_steps_per_second": 13.304,
+      "step": 4600
+    },
+    {
+      "epoch": 119.67479674796748,
+      "grad_norm": 0.9837270379066467,
+      "learning_rate": 4.003260869565217e-06,
+      "loss": 0.4777,
+      "step": 5520
+    },
+    {
+      "epoch": 119.67479674796748,
+      "eval_accuracy": 0.09730094466936572,
+      "eval_loss": 4.010466575622559,
+      "eval_runtime": 4.6403,
+      "eval_samples_per_second": 266.147,
+      "eval_steps_per_second": 13.361,
+      "step": 5520
+    },
+    {
+      "epoch": 139.62059620596207,
+      "grad_norm": 0.6684257388114929,
+      "learning_rate": 3.003260869565218e-06,
+      "loss": 0.472,
+      "step": 6440
+    },
+    {
+      "epoch": 139.62059620596207,
+      "eval_accuracy": 0.09647194910352805,
+      "eval_loss": 4.19666051864624,
+      "eval_runtime": 4.6605,
+      "eval_samples_per_second": 264.996,
+      "eval_steps_per_second": 13.303,
+      "step": 6440
+    },
+    {
+      "epoch": 159.56639566395663,
+      "grad_norm": 0.6181723475456238,
+      "learning_rate": 2.004347826086957e-06,
+      "loss": 0.472,
+      "step": 7360
+    },
+    {
+      "epoch": 159.56639566395663,
+      "eval_accuracy": 0.09544534412955466,
+      "eval_loss": 4.2893595695495605,
+      "eval_runtime": 4.6474,
+      "eval_samples_per_second": 265.737,
+      "eval_steps_per_second": 13.341,
+      "step": 7360
+    },
+    {
+      "epoch": 179.5121951219512,
+      "grad_norm": 0.7428745627403259,
+      "learning_rate": 1.0043478260869565e-06,
+      "loss": 0.4717,
+      "step": 8280
+    },
+    {
+      "epoch": 179.5121951219512,
+      "eval_accuracy": 0.09446693657219973,
+      "eval_loss": 4.415040493011475,
+      "eval_runtime": 4.6818,
+      "eval_samples_per_second": 263.79,
+      "eval_steps_per_second": 13.243,
+      "step": 8280
+    },
+    {
+      "epoch": 199.4579945799458,
+      "grad_norm": 0.6747769713401794,
+      "learning_rate": 4.3478260869565225e-09,
+      "loss": 0.4665,
+      "step": 9200
+    },
+    {
+      "epoch": 199.4579945799458,
+      "eval_accuracy": 0.09417004048582996,
+      "eval_loss": 4.4601263999938965,
+      "eval_runtime": 4.6453,
+      "eval_samples_per_second": 265.86,
+      "eval_steps_per_second": 13.347,
+      "step": 9200
+    },
+    {
+      "epoch": 199.4579945799458,
+      "step": 9200,
+      "total_flos": 7.267108691140301e+17,
+      "train_loss": 0.527852494612984,
+      "train_runtime": 15509.2666,
+      "train_samples_per_second": 118.806,
+      "train_steps_per_second": 0.593
+    }
+  ],
+  "logging_steps": 920,
+  "max_steps": 9200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 200,
+  "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": 7.267108691140301e+17,
+  "train_batch_size": 25,
+  "trial_name": null,
+  "trial_params": null
+}