add first version

README.md

@@ -1,3 +1,5 @@
+This model is a version of roberta which has been fine tuned for tokenclassification on the [LitBank](https://github.com/dbamman/litbank) dataset.
+
 ---
 license: cc-by-4.0
 ---

model_checkpoint/config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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": "B-FAC",
+    "1": "I-FAC",
+    "2": "B-GPE",
+    "3": "I-GPE",
+    "4": "B-LOC",
+    "5": "I-LOC",
+    "6": "B-ORG",
+    "7": "I-ORG",
+    "8": "B-PER",
+    "9": "I-PER",
+    "10": "B-VEH",
+    "11": "I-VEH",
+    "12": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-FAC": 0,
+    "B-GPE": 2,
+    "B-LOC": 4,
+    "B-ORG": 6,
+    "B-PER": 8,
+    "B-VEH": 10,
+    "I-FAC": 1,
+    "I-GPE": 3,
+    "I-LOC": 5,
+    "I-ORG": 7,
+    "I-PER": 9,
+    "I-VEH": 11,
+    "O": 12
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model_checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea2e481cfee2e9dc1637f1248b2d24f43748332fc25ee87742f06d0fcd3aaf6
+size 992635621

model_checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645ba5a76a0d7368e80a3f9a3fb036575d6ad18f6985037fdc50fc4bb838795e
+size 496331185

model_checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32559fd6c7a2d8e13383efb4399366cfdad968c5d2880cad28af28f6114404a0
+size 14503

model_checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e231269fa3e75d13bad1624c515df82db9983ec08876117767b357d3cb99cc9
+size 623

model_checkpoint/special_tokens_map.json

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

model_checkpoint/tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": true, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

model_checkpoint/trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 2625,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.047619047619048e-05,
+      "loss": 0.3398,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9404197400772744,
+      "eval_f1": 0.7127468581687613,
+      "eval_loss": 0.16514258086681366,
+      "eval_precision": 0.6821305841924399,
+      "eval_recall": 0.7462406015037594,
+      "eval_runtime": 8.3315,
+      "eval_samples_per_second": 96.741,
+      "eval_steps_per_second": 12.123,
+      "step": 875
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.095238095238095e-05,
+      "loss": 0.1895,
+      "step": 1000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.1346,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9471812434141201,
+      "eval_f1": 0.7536488279522335,
+      "eval_loss": 0.15585720539093018,
+      "eval_precision": 0.7117794486215538,
+      "eval_recall": 0.8007518796992481,
+      "eval_runtime": 8.3949,
+      "eval_samples_per_second": 96.011,
+      "eval_steps_per_second": 12.031,
+      "step": 1750
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.1163,
+      "step": 2000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.3809523809523808e-06,
+      "loss": 0.0711,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9476642079381805,
+      "eval_f1": 0.7592425608656447,
+      "eval_loss": 0.17694610357284546,
+      "eval_precision": 0.729636048526863,
+      "eval_recall": 0.7913533834586466,
+      "eval_runtime": 8.2863,
+      "eval_samples_per_second": 97.268,
+      "eval_steps_per_second": 12.189,
+      "step": 2625
+    }
+  ],
+  "max_steps": 2625,
+  "num_train_epochs": 3,
+  "total_flos": 697494389101650.0,
+  "trial_name": null,
+  "trial_params": null
+}

model_checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde37f84323c61f149d5d8177e1b6a413f7d8dc34f34ddb2909f69e7a23cc9a3
+size 3119