End of training

README.md

@@ -0,0 +1,64 @@
+---
+license: mit
+base_model: FacebookAI/roberta-large-mnli
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: paul-test-classification-roberta
+  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. -->
+
+# paul-test-classification-roberta
+
+This model is a fine-tuned version of [FacebookAI/roberta-large-mnli](https://huggingface.co/FacebookAI/roberta-large-mnli) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0
+- Accuracy: 1.0
+
+## 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: 64
+- eval_batch_size: 64
+- 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 | Accuracy |
+|:--------------:|:-----:|:----:|:---------------:|:--------:|
+| 44912717332.48 | 1.0   | 25   | 0.0             | 1.0      |
+| 0.0            | 2.0   | 50   | 0.0             | 1.0      |
+| 0.0            | 3.0   | 75   | 0.0             | 1.0      |
+| 0.0            | 4.0   | 100  | 0.0             | 1.0      |
+| 0.0            | 5.0   | 125  | 0.0             | 1.0      |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large-mnli",
+  "_num_labels": 3,
+  "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": "4.36.2",
+  "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 sha256:254ed2089bbdb259089a700335d022f88329570051153c0a8373c3702a551a5c
+size 1421495416

runs/Apr11_13-53-50_la1-gpu1.internetbrands.com/events.out.tfevents.1712868840.la1-gpu1.internetbrands.com.245979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730a61ec3506e75c5ef82fe157b0714885316216bfc5ea016c6df614b97e74dc
+size 7232

runs/Apr11_13-53-50_la1-gpu1.internetbrands.com/events.out.tfevents.1712869478.la1-gpu1.internetbrands.com.245979.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85cd3d756435becae7d50d04348fee92767ce92ea4e41ed52d011d38eab9b067
+size 405

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 +1,57 @@
+{
+  "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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b60ac953d5d6b54a92364e2483c2c3bebab879baa12c4622039f307a470c429
+size 4792