End of training

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: roberta-base_gpt-4o-2024-05-13_gpt-4o-mini-2024-07-18_20240913_044355
+  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. -->
+
+# roberta-base_gpt-4o-2024-05-13_gpt-4o-mini-2024-07-18_20240913_044355
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4503
+- Accuracy: 0.8026
+- F1: 0.8832
+- Precision: 0.8292
+- Recall: 0.9448
+
+## 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: 8
+- seed: 420
+- 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 | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.4781        | 1.0   | 871  | 0.4503          | 0.8026   | 0.8832 | 0.8292    | 0.9448 |
+| 0.4526        | 2.0   | 1742 | 0.4536          | 0.8048   | 0.8822 | 0.8434    | 0.9248 |
+| 0.424         | 3.0   | 2613 | 0.4529          | 0.8052   | 0.8837 | 0.8362    | 0.9370 |
+| 0.3789        | 4.0   | 3484 | 0.4970          | 0.8029   | 0.8826 | 0.8336    | 0.9379 |
+| 0.3275        | 5.0   | 4355 | 0.5587          | 0.7945   | 0.8777 | 0.8286    | 0.9330 |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8025848142164782,
+    "eval_f1": 0.883240970762469,
+    "eval_loss": 0.4503476321697235,
+    "eval_precision": 0.8292070326515967,
+    "eval_recall": 0.9448078495502862,
+    "eval_runtime": 28.88,
+    "eval_samples_per_second": 107.168,
+    "eval_steps_per_second": 13.4,
+    "test_samples": 3095,
+    "total_flos": 3.66540011222016e+16,
+    "train_loss": 0.4122221043408259,
+    "train_runtime": 3728.8568,
+    "train_samples": 27862,
+    "train_samples_per_second": 37.36,
+    "train_steps_per_second": 1.168
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baae04ea33eba37f6bbb4d354a8e9889c98eda6472879802651d6e7300065293
+size 498612824

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

test_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8025848142164782,
+    "eval_f1": 0.883240970762469,
+    "eval_loss": 0.4503476321697235,
+    "eval_precision": 0.8292070326515967,
+    "eval_recall": 0.9448078495502862,
+    "eval_runtime": 28.88,
+    "eval_samples_per_second": 107.168,
+    "eval_steps_per_second": 13.4,
+    "test_samples": 3095
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3.66540011222016e+16,
+    "train_loss": 0.4122221043408259,
+    "train_runtime": 3728.8568,
+    "train_samples": 27862,
+    "train_samples_per_second": 37.36,
+    "train_steps_per_second": 1.168
+}

trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 0.4503476321697235,
+  "best_model_checkpoint": "checkpoints/bert/roberta-base_gpt-4o-2024-05-13_gpt-4o-mini-2024-07-18_20240913_044355/checkpoint-871",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4355,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.2520592212677,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4781,
+      "step": 871
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8025848142164782,
+      "eval_f1": 0.883240970762469,
+      "eval_loss": 0.4503476321697235,
+      "eval_precision": 0.8292070326515967,
+      "eval_recall": 0.9448078495502862,
+      "eval_runtime": 28.9227,
+      "eval_samples_per_second": 107.009,
+      "eval_steps_per_second": 13.38,
+      "step": 871
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.9907314777374268,
+      "learning_rate": 1.2e-05,
+      "loss": 0.4526,
+      "step": 1742
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8048465266558966,
+      "eval_f1": 0.8822152886115444,
+      "eval_loss": 0.453591912984848,
+      "eval_precision": 0.843400447427293,
+      "eval_recall": 0.9247751430907605,
+      "eval_runtime": 28.9179,
+      "eval_samples_per_second": 107.027,
+      "eval_steps_per_second": 13.383,
+      "step": 1742
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.8395891189575195,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.424,
+      "step": 2613
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8051696284329564,
+      "eval_f1": 0.8837478311162522,
+      "eval_loss": 0.4529026448726654,
+      "eval_precision": 0.836191171105436,
+      "eval_recall": 0.9370400654129191,
+      "eval_runtime": 28.9142,
+      "eval_samples_per_second": 107.041,
+      "eval_steps_per_second": 13.384,
+      "step": 2613
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 11.389909744262695,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3789,
+      "step": 3484
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.802907915993538,
+      "eval_f1": 0.8826471719892266,
+      "eval_loss": 0.49696657061576843,
+      "eval_precision": 0.8335755813953488,
+      "eval_recall": 0.937857726901063,
+      "eval_runtime": 28.9149,
+      "eval_samples_per_second": 107.038,
+      "eval_steps_per_second": 13.384,
+      "step": 3484
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 11.702038764953613,
+      "learning_rate": 0.0,
+      "loss": 0.3275,
+      "step": 4355
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7945072697899839,
+      "eval_f1": 0.8776923076923077,
+      "eval_loss": 0.558699369430542,
+      "eval_precision": 0.8286129266521424,
+      "eval_recall": 0.9329517579721995,
+      "eval_runtime": 28.913,
+      "eval_samples_per_second": 107.045,
+      "eval_steps_per_second": 13.385,
+      "step": 4355
+    },
+    {
+      "epoch": 5.0,
+      "step": 4355,
+      "total_flos": 3.66540011222016e+16,
+      "train_loss": 0.4122221043408259,
+      "train_runtime": 3728.8568,
+      "train_samples_per_second": 37.36,
+      "train_steps_per_second": 1.168
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4355,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3.66540011222016e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a901c5ee0f415b18580c80834a8ac7b9aa6a2b92da61d1bee1cf6cc618dffa
+size 4984