Upload 14 files

cola/README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+language:
+- en
+license: apache-2.0
+base_model: google-bert/bert-base-cased
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- matthews_correlation
+model-index:
+- name: cola
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.6212584232587556
+---
+
+<!-- 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. -->
+
+# cola
+
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the GLUE COLA dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8440
+- Matthews Correlation: 0.6213
+
+## 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: 2.5e-05
+- train_batch_size: 32
+- 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: 6.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu118
+- Datasets 3.3.1
+- Tokenizers 0.21.0

cola/all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.8439584374427795,
+    "eval_matthews_correlation": 0.6212584232587556,
+    "eval_runtime": 2.0452,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 509.983,
+    "eval_steps_per_second": 64.053,
+    "total_flos": 3444607255477248.0,
+    "train_loss": 0.2595453208951808,
+    "train_runtime": 282.1547,
+    "train_samples": 8551,
+    "train_samples_per_second": 181.836,
+    "train_steps_per_second": 5.699
+}

cola/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": "cola",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 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
+}

cola/eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.8439584374427795,
+    "eval_matthews_correlation": 0.6212584232587556,
+    "eval_runtime": 2.0452,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 509.983,
+    "eval_steps_per_second": 64.053
+}

cola/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3914a1bf70fbecb9956a8d59981be21e5576bb355f0ab579504e817dd59f90c7
+size 440358464

cola/runs/May14_16-35-17_cs-Precision-7960-Tower/events.out.tfevents.1747254922.cs-Precision-7960-Tower.130992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab978f6f85953900c6734ffd3c4f91245121876a9ff5592ca2598c61a810052
+size 6124

cola/runs/May14_16-35-17_cs-Precision-7960-Tower/events.out.tfevents.1747255207.cs-Precision-7960-Tower.130992.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3521e2517a690ea4f4d14b15f8f324d643ee900860a8e57bc6a8994faddfcb17
+size 423

cola/special_tokens_map.json

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

cola/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]"
+}

cola/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 3444607255477248.0,
+    "train_loss": 0.2595453208951808,
+    "train_runtime": 282.1547,
+    "train_samples": 8551,
+    "train_samples_per_second": 181.836,
+    "train_steps_per_second": 5.699
+}

cola/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1608,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 11.32163143157959,
+      "learning_rate": 1.722636815920398e-05,
+      "loss": 0.5103,
+      "step": 500
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 6.54978609085083,
+      "learning_rate": 9.45273631840796e-06,
+      "loss": 0.2075,
+      "step": 1000
+    },
+    {
+      "epoch": 5.597014925373134,
+      "grad_norm": 0.33858296275138855,
+      "learning_rate": 1.6791044776119404e-06,
+      "loss": 0.1026,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "step": 1608,
+      "total_flos": 3444607255477248.0,
+      "train_loss": 0.2595453208951808,
+      "train_runtime": 282.1547,
+      "train_samples_per_second": 181.836,
+      "train_steps_per_second": 5.699
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1608,
+  "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": 3444607255477248.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

cola/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962a988eb1be8ecfc90ceb9c0fd20c2b520b2bd205c902f91a899823e3d647e1
+size 5304