End of training

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: google/bert_uncased_L-4_H-256_A-4
+tags:
+- generated_from_trainer
+model-index:
+- name: hangman-bert-mini
+  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. -->
+
+# hangman-bert-mini
+
+This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7279
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.9984        | 1.0   | 2609  | nan             |
+| 1.8901        | 2.0   | 5218  | 1.8151          |
+| 1.8457        | 3.0   | 7827  | 1.7514          |
+| 1.8219        | 4.0   | 10436 | 1.7348          |
+| 1.7865        | 5.0   | 13045 | 1.7279          |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.0.1
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b135d89d3304d6e60a4e6820946697995aec9bda587d891d74bf9c324ba232d
+size 44831439

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bbde95b7dfcbbfa75026c5d28fa996df746685384c7e921e3daf1f08939f4a
+size 4027