End of training

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert-base-uncased
+  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
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7784
+- Accuracy: 0.5
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.5,
+    "eval_loss": 1.7784260511398315,
+    "eval_runtime": 12.6206,
+    "eval_samples": 400,
+    "eval_samples_per_second": 31.694,
+    "eval_steps_per_second": 1.03,
+    "total_flos": 841955377152000.0,
+    "train_loss": 2.286143035888672,
+    "train_runtime": 314.1719,
+    "train_samples": 1600,
+    "train_samples_per_second": 10.186,
+    "train_steps_per_second": 0.637
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "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": "4.41.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.5,
+    "eval_loss": 1.7784260511398315,
+    "eval_runtime": 12.6206,
+    "eval_samples": 400,
+    "eval_samples_per_second": 31.694,
+    "eval_steps_per_second": 1.03
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b76bafec64dcdf5e8b0f34c0e6bea530f9e28be6c6f0ea4b91fe650575600f
+size 437958648

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 841955377152000.0,
+    "train_loss": 2.286143035888672,
+    "train_runtime": 314.1719,
+    "train_samples": 1600,
+    "train_samples_per_second": 10.186,
+    "train_steps_per_second": 0.637
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d6de96f93eb87ea81da7365422dc3d8de68ded9044925f89d219e7f5b70922
+size 5048