End of training

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert-base-uncased-finetuned-rte-run_3
+  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. -->
+
+# bert-base-uncased-finetuned-rte-run_3
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6457
+- Accuracy: 0.6606
+
+## 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: 3.50009902933741e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 39   | 0.6918          | 0.5271   |
+| No log        | 2.0   | 78   | 0.6407          | 0.6498   |
+| No log        | 3.0   | 117  | 0.6457          | 0.6606   |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "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:e8e82ce999f505702503f5280b6342cbe44c87f8ea6e80ee4f3dd2fa93ac77c7
+size 437958648

run-0/checkpoint-117/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-117/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ac66792066963804151e6788af71377ac80af960ede318603263e8a71fc0f1
+size 437958648

run-0/checkpoint-117/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63c1630ac509249f218e3274dfdbcccfb5409a8f16cb67a3024a44c7f8d8507
+size 876038394

run-0/checkpoint-117/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66062f09fb79eb516b32f1e74227740c5dc9e0025a015b9853db13b00b33e723
+size 14244

run-0/checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2062d22e00ae4657d5a2437cf8cf02f80d3f9a78be8bd9fd5b93e3e8134b5125
+size 1064

run-0/checkpoint-117/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-117/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]"
+}

run-0/checkpoint-117/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.6642599277978339,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-117",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6917867064476013,
+      "eval_runtime": 3.2048,
+      "eval_samples_per_second": 86.433,
+      "eval_steps_per_second": 1.56,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.6407069563865662,
+      "eval_runtime": 3.1725,
+      "eval_samples_per_second": 87.314,
+      "eval_steps_per_second": 1.576,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 0.6459211707115173,
+      "eval_runtime": 3.1766,
+      "eval_samples_per_second": 87.199,
+      "eval_steps_per_second": 1.574,
+      "step": 117
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.17661553519517478,
+    "learning_rate": 3.50009902933741e-05,
+    "max_length": 512,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc21828eae1c275563be6e7b84b6d4c4c581c53e194ae689da7d5222b7497bf
+size 5432

run-0/checkpoint-156/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac1eceb00174fe493c079fff1fbd36c37b46fa6b75c678175338eb3832ae867
+size 437958648

run-0/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a8109b61528f50f43568d61a2809776712bfbc241f5362c07c1f5c4c2bf079
+size 876038394

run-0/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2bd60aa42ae70430738a58c3189fe231933c3b00098640c8eda2327725ddc7
+size 14244

run-0/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7bbd17949f959de5a99d2de51c21954f2eaf6f4687a7cdbef223739c23f985
+size 1064

run-0/checkpoint-156/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-156/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]"
+}

run-0/checkpoint-156/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_global_step": 117,
+  "best_metric": 0.6823104693140795,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-117",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6064981949458483,
+      "eval_loss": 0.6656323671340942,
+      "eval_runtime": 3.229,
+      "eval_samples_per_second": 85.785,
+      "eval_steps_per_second": 1.548,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.6296112537384033,
+      "eval_runtime": 3.2312,
+      "eval_samples_per_second": 85.728,
+      "eval_steps_per_second": 1.547,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6823104693140795,
+      "eval_loss": 0.6674417853355408,
+      "eval_runtime": 3.1663,
+      "eval_samples_per_second": 87.483,
+      "eval_steps_per_second": 1.579,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.7529056072235107,
+      "eval_runtime": 3.1735,
+      "eval_samples_per_second": 87.285,
+      "eval_steps_per_second": 1.576,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 156,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.32872199298996635,
+    "learning_rate": 4.9534002785729435e-05,
+    "max_length": 256,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79af4227a137db021853d20370fdd1d2ea42b3a338e96a6c3a7f2ad6c7e573c
+size 5432

run-0/checkpoint-195/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-195/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b8d01ea1fa03fecb27d3824ef48321dd292022de2980ec8cd85ee43a3a31cb
+size 437958648

run-0/checkpoint-195/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bb59c695dd3a9f11f5c62fe22bb5282124d32d9410ffc137cda9e60aeffb60
+size 876038394

run-0/checkpoint-195/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e2e34b39683502d4d6915c71fb35228270e1cba7227213b6a9df68b951484b
+size 14244

run-0/checkpoint-195/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278bb2692df60b8433969a78547b13bdd26f2d247316b5de7f891cadbc378ef4
+size 1064

run-0/checkpoint-195/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-195/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]"
+}

run-0/checkpoint-195/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.6931407942238267,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-156",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 195,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.6601823568344116,
+      "eval_runtime": 3.2169,
+      "eval_samples_per_second": 86.108,
+      "eval_steps_per_second": 1.554,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.6585440635681152,
+      "eval_runtime": 3.167,
+      "eval_samples_per_second": 87.464,
+      "eval_steps_per_second": 1.579,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6750902527075813,
+      "eval_loss": 0.6770333051681519,
+      "eval_runtime": 3.1901,
+      "eval_samples_per_second": 86.831,
+      "eval_steps_per_second": 1.567,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.811002790927887,
+      "eval_runtime": 3.1876,
+      "eval_samples_per_second": 86.9,
+      "eval_steps_per_second": 1.569,
+      "step": 156
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6823104693140795,
+      "eval_loss": 0.8974205851554871,
+      "eval_runtime": 3.1823,
+      "eval_samples_per_second": 87.045,
+      "eval_steps_per_second": 1.571,
+      "step": 195
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.18213454295456433,
+    "learning_rate": 3.6493270590502144e-05,
+    "max_length": 128,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-195/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229c1e8ce32265f4785c2f1fc6c5974e8e794c5f13183f0befbbf5834964686e
+size 5432

run-0/checkpoint-234/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-234/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e1f2592db36d89fc4a1436eeb99d8f64588b68868d3187795c220c6fd54ae0
+size 437958648

run-0/checkpoint-234/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded49ae56a161dea9cc1794f19d43250327ec9b8e5af194d2f03cb961feaf422
+size 876038394

run-0/checkpoint-234/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c335e518260c2aab1d76d67154f45cb6ec7612dd36ed4defaf4739071e2e0de
+size 14244

run-0/checkpoint-234/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795acc3a991d2adea7b7d2df172627ff581631ec207324bc6948cc49fceaa143
+size 1064

run-0/checkpoint-234/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-234/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]"
+}

run-0/checkpoint-234/trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_global_step": 156,
+  "best_metric": 0.6931407942238267,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-156",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 234,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.6601823568344116,
+      "eval_runtime": 3.2169,
+      "eval_samples_per_second": 86.108,
+      "eval_steps_per_second": 1.554,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6498194945848376,
+      "eval_loss": 0.6585440635681152,
+      "eval_runtime": 3.167,
+      "eval_samples_per_second": 87.464,
+      "eval_steps_per_second": 1.579,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6750902527075813,
+      "eval_loss": 0.6770333051681519,
+      "eval_runtime": 3.1901,
+      "eval_samples_per_second": 86.831,
+      "eval_steps_per_second": 1.567,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.811002790927887,
+      "eval_runtime": 3.1876,
+      "eval_samples_per_second": 86.9,
+      "eval_steps_per_second": 1.569,
+      "step": 156
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6823104693140795,
+      "eval_loss": 0.8974205851554871,
+      "eval_runtime": 3.1823,
+      "eval_samples_per_second": 87.045,
+      "eval_steps_per_second": 1.571,
+      "step": 195
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.9125683307647705,
+      "eval_runtime": 3.182,
+      "eval_samples_per_second": 87.053,
+      "eval_steps_per_second": 1.571,
+      "step": 234
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "dropout_rate": 0.18213454295456433,
+    "learning_rate": 3.6493270590502144e-05,
+    "max_length": 128,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 64
+  }
+}

run-0/checkpoint-234/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229c1e8ce32265f4785c2f1fc6c5974e8e794c5f13183f0befbbf5834964686e
+size 5432

run-0/checkpoint-39/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-39/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5666a40d81e971b7e328323dbaf5b586dc7d08eb3b80e5d286b3aa1f944fa1b
+size 437958648

run-0/checkpoint-39/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704af016b770a116f5c042e898063e2e8eec492a362fd0c63bfc5270a583ac44
+size 876038394