End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: mit
+base_model: roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-base_brkfst_trainer
+  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_brkfst_trainer
+
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0782
+- Accuracy: 0.98
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 27
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6559        | 0.71  | 10   | 0.6907          | 0.8      |
+| 0.5465        | 1.43  | 20   | 0.3822          | 0.84     |
+| 0.4035        | 2.14  | 30   | 0.3178          | 0.93     |
+| 0.3651        | 2.86  | 40   | 0.1117          | 0.94     |
+| 0.1986        | 3.57  | 50   | 0.1832          | 0.95     |
+| 0.2985        | 4.29  | 60   | 0.1133          | 0.96     |
+| 0.141         | 5.0   | 70   | 0.1594          | 0.97     |
+| 0.1334        | 5.71  | 80   | 0.2771          | 0.96     |
+| 0.1874        | 6.43  | 90   | 0.0757          | 0.95     |
+| 0.0594        | 7.14  | 100  | 0.2082          | 0.95     |
+| 0.2883        | 7.86  | 110  | 0.2366          | 0.96     |
+| 0.0459        | 8.57  | 120  | 0.1599          | 0.96     |
+| 0.0733        | 9.29  | 130  | 0.2568          | 0.96     |
+| 0.0483        | 10.0  | 140  | 0.3639          | 0.94     |
+| 0.0487        | 10.71 | 150  | 0.2121          | 0.97     |
+| 0.0339        | 11.43 | 160  | 0.1368          | 0.98     |
+| 0.0463        | 12.14 | 170  | 0.1465          | 0.98     |
+| 0.0025        | 12.86 | 180  | 0.2487          | 0.96     |
+| 0.0009        | 13.57 | 190  | 0.0968          | 0.98     |
+| 0.0003        | 14.29 | 200  | 0.0710          | 0.98     |
+| 0.0003        | 15.0  | 210  | 0.0782          | 0.98     |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "roberta-large",
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

logs/events.out.tfevents.1721902457.066bd0ebbba0.1516.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96aa2c937e6efd11f90e37643b2a75b5b2e9ce3326c68b6ff3e53f9ab66e13cf
+size 16063

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e698f46525ae24073e99c0f13cf2a452d0ae3c1b3b6e754c67dbcb1984317d6
+size 1421495416

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>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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>",
+  "do_lower_case": true,
+  "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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d044177b24a8c0b20b87ed1cbb7cc49f358d5583bae788e48dd7534cacfb061
+size 4920