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: 3.5401
-- Accuracy: 0.0640
+- Accuracy: 0.0635
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 59.820761762509335,
+    "eval_accuracy": 0.06350342570815012,
+    "eval_loss": 3.5401461124420166,
+    "eval_runtime": 27.0698,
+    "eval_samples_per_second": 262.729,
+    "eval_steps_per_second": 13.151,
+    "total_flos": 1.2667425775753882e+18,
+    "train_loss": 1.5184656874219726,
+    "train_runtime": 28586.6077,
+    "train_samples_per_second": 112.387,
+    "train_steps_per_second": 0.56
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 59.820761762509335,
+    "eval_accuracy": 0.06350342570815012,
+    "eval_loss": 3.5401461124420166,
+    "eval_runtime": 27.0698,
+    "eval_samples_per_second": 262.729,
+    "eval_steps_per_second": 13.151
+}

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": 59.820761762509335,
+    "total_flos": 1.2667425775753882e+18,
+    "train_loss": 1.5184656874219726,
+    "train_runtime": 28586.6077,
+    "train_samples_per_second": 112.387,
+    "train_steps_per_second": 0.56
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 59.820761762509335,
+  "eval_steps": 1602,
+  "global_step": 16020,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.982076176250933,
+      "grad_norm": 1.965578317642212,
+      "learning_rate": 9.001248439450687e-06,
+      "loss": 1.7271,
+      "step": 1602
+    },
+    {
+      "epoch": 5.982076176250933,
+      "eval_accuracy": 0.07888076490438695,
+      "eval_loss": 3.0069968700408936,
+      "eval_runtime": 27.4304,
+      "eval_samples_per_second": 259.274,
+      "eval_steps_per_second": 12.978,
+      "step": 1602
+    },
+    {
+      "epoch": 11.964152352501866,
+      "grad_norm": 5.727398872375488,
+      "learning_rate": 8.001248439450687e-06,
+      "loss": 1.6271,
+      "step": 3204
+    },
+    {
+      "epoch": 11.964152352501866,
+      "eval_accuracy": 0.07318616422947131,
+      "eval_loss": 3.151439666748047,
+      "eval_runtime": 26.734,
+      "eval_samples_per_second": 266.029,
+      "eval_steps_per_second": 13.316,
+      "step": 3204
+    },
+    {
+      "epoch": 17.9462285287528,
+      "grad_norm": 5.7716898918151855,
+      "learning_rate": 7.002496878901374e-06,
+      "loss": 1.552,
+      "step": 4806
+    },
+    {
+      "epoch": 17.9462285287528,
+      "eval_accuracy": 0.07049118860142482,
+      "eval_loss": 3.151090621948242,
+      "eval_runtime": 26.8156,
+      "eval_samples_per_second": 265.218,
+      "eval_steps_per_second": 13.276,
+      "step": 4806
+    },
+    {
+      "epoch": 23.928304705003733,
+      "grad_norm": 2.6458210945129395,
+      "learning_rate": 6.002496878901374e-06,
+      "loss": 1.5094,
+      "step": 6408
+    },
+    {
+      "epoch": 23.928304705003733,
+      "eval_accuracy": 0.06840551181102363,
+      "eval_loss": 3.3705952167510986,
+      "eval_runtime": 26.7683,
+      "eval_samples_per_second": 265.687,
+      "eval_steps_per_second": 13.299,
+      "step": 6408
+    },
+    {
+      "epoch": 29.910380881254667,
+      "grad_norm": 4.236194133758545,
+      "learning_rate": 5.002496878901374e-06,
+      "loss": 1.484,
+      "step": 8010
+    },
+    {
+      "epoch": 29.910380881254667,
+      "eval_accuracy": 0.06718222722159731,
+      "eval_loss": 3.4197287559509277,
+      "eval_runtime": 26.7706,
+      "eval_samples_per_second": 265.665,
+      "eval_steps_per_second": 13.298,
+      "step": 8010
+    },
+    {
+      "epoch": 35.8924570575056,
+      "grad_norm": 1.0438162088394165,
+      "learning_rate": 4.003121098626717e-06,
+      "loss": 1.4683,
+      "step": 9612
+    },
+    {
+      "epoch": 35.8924570575056,
+      "eval_accuracy": 0.0666010498687664,
+      "eval_loss": 3.527012586593628,
+      "eval_runtime": 26.8167,
+      "eval_samples_per_second": 265.208,
+      "eval_steps_per_second": 13.275,
+      "step": 9612
+    },
+    {
+      "epoch": 41.87453323375654,
+      "grad_norm": 1.4691572189331055,
+      "learning_rate": 3.0037453183520603e-06,
+      "loss": 1.4567,
+      "step": 11214
+    },
+    {
+      "epoch": 41.87453323375654,
+      "eval_accuracy": 0.06578418769082436,
+      "eval_loss": 3.4933013916015625,
+      "eval_runtime": 26.8665,
+      "eval_samples_per_second": 264.716,
+      "eval_steps_per_second": 13.251,
+      "step": 11214
+    },
+    {
+      "epoch": 47.856609410007465,
+      "grad_norm": 1.4771349430084229,
+      "learning_rate": 2.004369538077403e-06,
+      "loss": 1.4541,
+      "step": 12816
+    },
+    {
+      "epoch": 47.856609410007465,
+      "eval_accuracy": 0.06527699662542182,
+      "eval_loss": 3.4873604774475098,
+      "eval_runtime": 26.963,
+      "eval_samples_per_second": 263.769,
+      "eval_steps_per_second": 13.203,
+      "step": 12816
+    },
+    {
+      "epoch": 53.8386855862584,
+      "grad_norm": 2.609039783477783,
+      "learning_rate": 1.0049937578027467e-06,
+      "loss": 1.4539,
+      "step": 14418
+    },
+    {
+      "epoch": 53.8386855862584,
+      "eval_accuracy": 0.06455443069616298,
+      "eval_loss": 3.530477285385132,
+      "eval_runtime": 26.6641,
+      "eval_samples_per_second": 266.726,
+      "eval_steps_per_second": 13.351,
+      "step": 14418
+    },
+    {
+      "epoch": 59.820761762509335,
+      "grad_norm": 0.7880098223686218,
+      "learning_rate": 4.993757802746567e-09,
+      "loss": 1.452,
+      "step": 16020
+    },
+    {
+      "epoch": 59.820761762509335,
+      "eval_accuracy": 0.0639763779527559,
+      "eval_loss": 3.5401461124420166,
+      "eval_runtime": 27.1718,
+      "eval_samples_per_second": 261.742,
+      "eval_steps_per_second": 13.102,
+      "step": 16020
+    },
+    {
+      "epoch": 59.820761762509335,
+      "step": 16020,
+      "total_flos": 1.2667425775753882e+18,
+      "train_loss": 1.5184656874219726,
+      "train_runtime": 28586.6077,
+      "train_samples_per_second": 112.387,
+      "train_steps_per_second": 0.56
+    }
+  ],
+  "logging_steps": 1602,
+  "max_steps": 16020,
+  "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": 1.2667425775753882e+18,
+  "train_batch_size": 20,
+  "trial_name": null,
+  "trial_params": null
+}