Add model

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d02fa3f5e6410fcd1098223136d7895c435bb1a61f087ea48862f8366a0731
+size 1736198447

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "name_or_path": "microsoft/deberta-v3-large",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": 0.7603706972639012,
+  "best_model_checkpoint": "./outputs/deberta-large-output/vua_metaphor_8_0.01_0.00002_03-21-23_22-02/checkpoint-3612",
+  "epoch": 3.999584889995849,
+  "global_step": 4816,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.595758780649437e-05,
+      "loss": 0.1306,
+      "step": 1204
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9674111647440617,
+      "eval_f1": 0.7417333045169656,
+      "eval_loss": 0.08462577313184738,
+      "eval_precision": 0.7609756097560976,
+      "eval_recall": 0.7234401349072512,
+      "eval_runtime": 13.8793,
+      "eval_samples_per_second": 173.64,
+      "eval_steps_per_second": 21.759,
+      "step": 1204
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.0638391870996245e-05,
+      "loss": 0.0527,
+      "step": 2408
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9700564509531212,
+      "eval_f1": 0.7538116591928251,
+      "eval_loss": 0.08208993822336197,
+      "eval_precision": 0.8050766283524904,
+      "eval_recall": 0.7086846543001686,
+      "eval_runtime": 13.6308,
+      "eval_samples_per_second": 176.806,
+      "eval_steps_per_second": 22.156,
+      "step": 2408
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.319195935498122e-06,
+      "loss": 0.0189,
+      "step": 3612
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9703837028552729,
+      "eval_f1": 0.7603706972639012,
+      "eval_loss": 0.11565817892551422,
+      "eval_precision": 0.7976851851851852,
+      "eval_recall": 0.7263912310286678,
+      "eval_runtime": 15.1081,
+      "eval_samples_per_second": 159.517,
+      "eval_steps_per_second": 19.989,
+      "step": 3612
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.006,
+      "step": 4816
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9703564318634269,
+      "eval_f1": 0.7563326608383771,
+      "eval_loss": 0.15718454122543335,
+      "eval_precision": 0.8075634274772618,
+      "eval_recall": 0.7112141652613828,
+      "eval_runtime": 13.5443,
+      "eval_samples_per_second": 177.934,
+      "eval_steps_per_second": 22.297,
+      "step": 4816
+    },
+    {
+      "epoch": 4.0,
+      "step": 4816,
+      "total_flos": 2366884617110520.0,
+      "train_loss": 0.052028106791632514,
+      "train_runtime": 1649.8443,
+      "train_samples_per_second": 23.355,
+      "train_steps_per_second": 2.919
+    }
+  ],
+  "max_steps": 4816,
+  "num_train_epochs": 4,
+  "total_flos": 2366884617110520.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b300369869789a9859c619ff5bbc2b073c0912918a1fb0d20e9bafe3a0d6503
+size 3311