Upload 14 files

mrpc/README.md

@@ -0,0 +1,79 @@
+---
+library_name: transformers
+language:
+- en
+license: apache-2.0
+base_model: google-bert/bert-base-cased
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model-index:
+- name: mrpc
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8725490196078431
+    - name: F1
+      type: f1
+      value: 0.910958904109589
+---
+
+<!-- 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. -->
+
+# mrpc
+
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the GLUE MRPC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5399
+- Accuracy: 0.8725
+- F1: 0.9110
+- Combined Score: 0.8918
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use 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: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu118
+- Datasets 3.3.1
+- Tokenizers 0.21.0

mrpc/all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8725490196078431,
+    "eval_combined_score": 0.891753961858716,
+    "eval_f1": 0.910958904109589,
+    "eval_loss": 0.5399143695831299,
+    "eval_runtime": 0.8251,
+    "eval_samples": 408,
+    "eval_samples_per_second": 494.496,
+    "eval_steps_per_second": 61.812,
+    "total_flos": 985055893118976.0,
+    "train_loss": 0.3395414849986201,
+    "train_runtime": 89.4666,
+    "train_samples": 3668,
+    "train_samples_per_second": 163.994,
+    "train_steps_per_second": 10.283
+}

mrpc/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google-bert/bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "mrpc",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "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": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

mrpc/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8725490196078431,
+    "eval_combined_score": 0.891753961858716,
+    "eval_f1": 0.910958904109589,
+    "eval_loss": 0.5399143695831299,
+    "eval_runtime": 0.8251,
+    "eval_samples": 408,
+    "eval_samples_per_second": 494.496,
+    "eval_steps_per_second": 61.812
+}

mrpc/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9492794b72d674bd0e8cb9ba3455416752f99dad63b9b55562aac0ee528ffa57
+size 440358464

mrpc/runs/May14_17-06-57_cs-Precision-7960-Tower/events.out.tfevents.1747256822.cs-Precision-7960-Tower.131643.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e48df50fb7f20a8f1ddc6fa8a3013fa18dda524cf4c5a0c62d189a6a5e5df88
+size 5702

mrpc/runs/May14_17-06-57_cs-Precision-7960-Tower/events.out.tfevents.1747256913.cs-Precision-7960-Tower.131643.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228b39ae0e48b8fdf55f22f1b803c3b359889f8e18b09e9f6fb128e89a8714a6
+size 515

mrpc/special_tokens_map.json

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

mrpc/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": false,
+  "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]"
+}

mrpc/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 985055893118976.0,
+    "train_loss": 0.3395414849986201,
+    "train_runtime": 89.4666,
+    "train_samples": 3668,
+    "train_samples_per_second": 163.994,
+    "train_steps_per_second": 10.283
+}

mrpc/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 920,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 3.317793846130371,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 0.5041,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "step": 920,
+      "total_flos": 985055893118976.0,
+      "train_loss": 0.3395414849986201,
+      "train_runtime": 89.4666,
+      "train_samples_per_second": 163.994,
+      "train_steps_per_second": 10.283
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 920,
+  "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": 985055893118976.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

mrpc/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b34c004b1c606688816e6cfc4add9152220b152e2bb661d5bd6de763104feee
+size 5304