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: 8.0173
-- Accuracy: 0.0636
+- Accuracy: 0.0640
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 199.4579945799458,
+    "eval_accuracy": 0.06396761133603239,
+    "eval_loss": 8.017308235168457,
+    "eval_runtime": 4.52,
+    "eval_samples_per_second": 273.23,
+    "eval_steps_per_second": 13.717,
+    "total_flos": 7.274565728868803e+17,
+    "train_loss": 0.6285194662342901,
+    "train_runtime": 15527.0261,
+    "train_samples_per_second": 118.671,
+    "train_steps_per_second": 0.593
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 199.4579945799458,
+    "eval_accuracy": 0.06396761133603239,
+    "eval_loss": 8.017308235168457,
+    "eval_runtime": 4.52,
+    "eval_samples_per_second": 273.23,
+    "eval_steps_per_second": 13.717
+}

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": 7.274565728868803e+17,
+    "train_loss": 0.6285194662342901,
+    "train_runtime": 15527.0261,
+    "train_samples_per_second": 118.671,
+    "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": 3.2469282150268555,
+      "learning_rate": 9.009782608695652e-06,
+      "loss": 1.145,
+      "step": 920
+    },
+    {
+      "epoch": 19.94579945799458,
+      "eval_accuracy": 0.06477732793522267,
+      "eval_loss": 3.420142412185669,
+      "eval_runtime": 4.7595,
+      "eval_samples_per_second": 259.481,
+      "eval_steps_per_second": 13.027,
+      "step": 920
+    },
+    {
+      "epoch": 39.89159891598916,
+      "grad_norm": 7.137430191040039,
+      "learning_rate": 8.009782608695653e-06,
+      "loss": 0.8113,
+      "step": 1840
+    },
+    {
+      "epoch": 39.89159891598916,
+      "eval_accuracy": 0.06558704453441296,
+      "eval_loss": 4.794512748718262,
+      "eval_runtime": 4.6738,
+      "eval_samples_per_second": 264.237,
+      "eval_steps_per_second": 13.265,
+      "step": 1840
+    },
+    {
+      "epoch": 59.83739837398374,
+      "grad_norm": 6.65213680267334,
+      "learning_rate": 7.0097826086956536e-06,
+      "loss": 0.6672,
+      "step": 2760
+    },
+    {
+      "epoch": 59.83739837398374,
+      "eval_accuracy": 0.0620782726045884,
+      "eval_loss": 5.849432468414307,
+      "eval_runtime": 4.6724,
+      "eval_samples_per_second": 264.32,
+      "eval_steps_per_second": 13.27,
+      "step": 2760
+    },
+    {
+      "epoch": 79.78319783197831,
+      "grad_norm": 7.155282497406006,
+      "learning_rate": 6.009782608695652e-06,
+      "loss": 0.5974,
+      "step": 3680
+    },
+    {
+      "epoch": 79.78319783197831,
+      "eval_accuracy": 0.060931174089068826,
+      "eval_loss": 6.682722568511963,
+      "eval_runtime": 4.7013,
+      "eval_samples_per_second": 262.693,
+      "eval_steps_per_second": 13.188,
+      "step": 3680
+    },
+    {
+      "epoch": 99.7289972899729,
+      "grad_norm": 9.478208541870117,
+      "learning_rate": 5.009782608695652e-06,
+      "loss": 0.5557,
+      "step": 4600
+    },
+    {
+      "epoch": 99.7289972899729,
+      "eval_accuracy": 0.062348178137651825,
+      "eval_loss": 7.22858190536499,
+      "eval_runtime": 4.645,
+      "eval_samples_per_second": 265.878,
+      "eval_steps_per_second": 13.348,
+      "step": 4600
+    },
+    {
+      "epoch": 119.67479674796748,
+      "grad_norm": 4.209677219390869,
+      "learning_rate": 4.009782608695653e-06,
+      "loss": 0.5305,
+      "step": 5520
+    },
+    {
+      "epoch": 119.67479674796748,
+      "eval_accuracy": 0.06275303643724696,
+      "eval_loss": 8.140605926513672,
+      "eval_runtime": 4.6969,
+      "eval_samples_per_second": 262.941,
+      "eval_steps_per_second": 13.2,
+      "step": 5520
+    },
+    {
+      "epoch": 139.62059620596207,
+      "grad_norm": 2.9163646697998047,
+      "learning_rate": 3.009782608695652e-06,
+      "loss": 0.5093,
+      "step": 6440
+    },
+    {
+      "epoch": 139.62059620596207,
+      "eval_accuracy": 0.06350491613649509,
+      "eval_loss": 7.877014636993408,
+      "eval_runtime": 4.6354,
+      "eval_samples_per_second": 266.425,
+      "eval_steps_per_second": 13.375,
+      "step": 6440
+    },
+    {
+      "epoch": 159.56639566395663,
+      "grad_norm": 2.5000979900360107,
+      "learning_rate": 2.0097826086956523e-06,
+      "loss": 0.4975,
+      "step": 7360
+    },
+    {
+      "epoch": 159.56639566395663,
+      "eval_accuracy": 0.06305668016194332,
+      "eval_loss": 7.953996181488037,
+      "eval_runtime": 4.665,
+      "eval_samples_per_second": 264.738,
+      "eval_steps_per_second": 13.29,
+      "step": 7360
+    },
+    {
+      "epoch": 179.5121951219512,
+      "grad_norm": 4.382449626922607,
+      "learning_rate": 1.0097826086956521e-06,
+      "loss": 0.4903,
+      "step": 8280
+    },
+    {
+      "epoch": 179.5121951219512,
+      "eval_accuracy": 0.06324786324786325,
+      "eval_loss": 7.8320698738098145,
+      "eval_runtime": 4.6898,
+      "eval_samples_per_second": 263.337,
+      "eval_steps_per_second": 13.22,
+      "step": 8280
+    },
+    {
+      "epoch": 199.4579945799458,
+      "grad_norm": 2.3895769119262695,
+      "learning_rate": 9.782608695652175e-09,
+      "loss": 0.481,
+      "step": 9200
+    },
+    {
+      "epoch": 199.4579945799458,
+      "eval_accuracy": 0.06364372469635628,
+      "eval_loss": 8.017308235168457,
+      "eval_runtime": 4.7442,
+      "eval_samples_per_second": 260.32,
+      "eval_steps_per_second": 13.069,
+      "step": 9200
+    },
+    {
+      "epoch": 199.4579945799458,
+      "step": 9200,
+      "total_flos": 7.274565728868803e+17,
+      "train_loss": 0.6285194662342901,
+      "train_runtime": 15527.0261,
+      "train_samples_per_second": 118.671,
+      "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": 7.274565728868803e+17,
+  "train_batch_size": 25,
+  "trial_name": null,
+  "trial_params": null
+}