essay-scoring-v1

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: 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. -->
+
+# model
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9688
+- F1: [0.55895197 0.65655471 0.64079208 0.61947973 0.4622871  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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1                                                                  |
+|:-------------:|:------:|:----:|:---------------:|:-------------------------------------------------------------------:|
+| 1.1276        | 0.2889 | 500  | 1.0034          | [0.         0.64762876 0.62495426 0.58732057 0.23529412 0.        ] |
+| 0.9959        | 0.5777 | 1000 | 0.9698          | [0.         0.65695931 0.58746415 0.59628074 0.         0.        ] |
+| 1.0332        | 0.8666 | 1500 | 0.9243          | [0.56649396 0.62368113 0.65886525 0.57998639 0.42633229 0.        ] |
+| 0.9629        | 1.1554 | 2000 | 0.9520          | [0.4842615  0.65972551 0.63432836 0.5464191  0.01117318 0.        ] |
+| 1.1092        | 1.4443 | 2500 | 0.9043          | [0.58064516 0.61299597 0.63804173 0.63392347 0.09090909 0.        ] |
+| 0.7352        | 1.7331 | 3000 | 0.9064          | [0.5703125  0.65753425 0.65755449 0.57650273 0.44675325 0.        ] |
+| 0.8081        | 2.0220 | 3500 | 0.9160          | [0.57377049 0.65274725 0.64854518 0.5620389  0.44813278 0.        ] |
+| 0.6783        | 2.3108 | 4000 | 0.9415          | [0.59016393 0.66339334 0.65859375 0.61950287 0.496614   0.        ] |
+| 0.8309        | 2.5997 | 4500 | 0.9317          | [0.59960552 0.6642144  0.63559663 0.63245823 0.42767296 0.        ] |
+| 0.5363        | 2.8885 | 5000 | 0.9688          | [0.55895197 0.65655471 0.64079208 0.61947973 0.4622871  0.        ] |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,44 @@
+{
+  "_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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "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:ab944625664057c07d8ebf666a20ebf0274daae18dd2a52b406564480768aad6
+size 243444320

runs/Apr29_23-45-16_b336ac26e23b/events.out.tfevents.1714434327.b336ac26e23b.1897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78dc3a3cef15070f373d8c3999c72706712c6fbee7eb5913d0bb3f500b8ba61
+size 117425

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:d881dbb58225f42468bfe11313b1a30d838ad612fa61aa3c9b1447a14a42d1d9
+size 4984