End of training

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: my_awesome_model
+  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. -->
+
+# my_awesome_model
+
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3326
+- Accuracy: 0.3333
+
+## 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: 8
+- eval_batch_size: 8
+- 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: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 2    | 1.5154          | 0.3333   |
+| No log        | 2.0   | 4    | 1.3792          | 0.3333   |
+| No log        | 3.0   | 6    | 1.3326          | 0.3333   |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "google-bert/bert-base-cased",
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e0fc4de66b63fe86c27bb9e8124dd5833f281a5cc5b3fc1cc3c7370a7afeb7d
+size 433279996

runs/Nov21_23-18-12_leo-ThinkPad-T470p/events.out.tfevents.1732253441.leo-ThinkPad-T470p.1470106.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c053da7aa66b9d0df955a6e55c52ec0d92172154fbdffe5ca1f5b60ca80b094
+size 405

runs/Nov21_23-34-04_leo-ThinkPad-T470p/events.out.tfevents.1732253645.leo-ThinkPad-T470p.1484888.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbaebf9ab660bd2d7bc9f43030112bce15eee1a321b144f74cb7120836e8526c
+size 6627

runs/Nov21_23-34-04_leo-ThinkPad-T470p/events.out.tfevents.1732253782.leo-ThinkPad-T470p.1484888.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157926bb9339cab6650c805983d129f0bfeec5ced6b30ea17c0390b157dbc27c
+size 405

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3333333333333333,
+      "eval_loss": 1.5153735876083374,
+      "eval_runtime": 6.5784,
+      "eval_samples_per_second": 2.28,
+      "eval_steps_per_second": 0.304,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3333333333333333,
+      "eval_loss": 1.3791700601577759,
+      "eval_runtime": 8.0079,
+      "eval_samples_per_second": 1.873,
+      "eval_steps_per_second": 0.25,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3333333333333333,
+      "eval_loss": 1.3326424360275269,
+      "eval_runtime": 8.569,
+      "eval_samples_per_second": 1.751,
+      "eval_steps_per_second": 0.233,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "step": 6,
+      "total_flos": 11840316410880.0,
+      "train_loss": 1.5828933715820312,
+      "train_runtime": 108.0308,
+      "train_samples_per_second": 0.417,
+      "train_steps_per_second": 0.056
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3333333333333333,
+      "eval_loss": 1.3326424360275269,
+      "eval_runtime": 6.5661,
+      "eval_samples_per_second": 2.284,
+      "eval_steps_per_second": 0.305,
+      "step": 6
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6,
+  "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": 11840316410880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51737b5157baec0337607a85ff33ff02fe581a0afc08b502331a63da7a4cb80b
+size 5304