End of training

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: test-micse
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# test-micse
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 48
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "BertForCL"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_probs_dropout_prob_noise": 0.15,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob_noise": 0.15,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "task_alpha": 1.0,
+  "task_lambda": 0.0001,
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5399330b9c5fbd59da0278bed0714d4edb562f45423fb07183c11e19c512e28
+size 437952304

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.4685486555099487,
+      "learning_rate": 9.242424242424244e-06,
+      "loss": 0.2565,
+      "step": 10
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 2.9761343002319336,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 0.282,
+      "step": 20
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 2.0076684951782227,
+      "learning_rate": 6.212121212121213e-06,
+      "loss": 0.2094,
+      "step": 30
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 2.965219259262085,
+      "learning_rate": 4.696969696969698e-06,
+      "loss": 0.2262,
+      "step": 40
+    },
+    {
+      "epoch": 7.142857142857143,
+      "grad_norm": 0.9869125485420227,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 0.2018,
+      "step": 50
+    },
+    {
+      "epoch": 8.571428571428571,
+      "grad_norm": 2.1355133056640625,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.1887,
+      "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.18442638218402863,
+      "learning_rate": 1.5151515151515152e-07,
+      "loss": 0.155,
+      "step": 70
+    },
+    {
+      "epoch": 10.0,
+      "step": 70,
+      "total_flos": 32797848526848.0,
+      "train_loss": 0.21707289997639756,
+      "train_runtime": 15.5227,
+      "train_samples_per_second": 64.422,
+      "train_steps_per_second": 4.51
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 70,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 32797848526848.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126fd45bbd7f42e75111d62b0ecb7896058e4aa28b44a50c6a6919197bb1459a
+size 5777