Add model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "microsoft/mdeberta-v3-base",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "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": 251000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12840fe87dd6b685f874c76b92d3acb08f689d7a00d6bc39b8fc08597700ecff
+size 1112955823

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 sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f06fc3bbcbbc8f07be861b9a6a69e177247bc549b2bcbf0483e4dd98c06b6f6
+size 16331301

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/mdeberta-v3-base",
+  "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": 0.9878331402085747,
+  "best_model_checkpoint": "./outputs/mdeberta-v3-base-output/cometa_8_0.01_0.00005_09-08-22_17-20/checkpoint-1456",
+  "epoch": 4.0,
+  "global_step": 1456,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.991228070175439e-05,
+      "loss": 0.0899,
+      "step": 364
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9917505892436255,
+      "eval_f1": 0.744355909694555,
+      "eval_loss": 0.022882504388689995,
+      "eval_precision": 0.8629715165511932,
+      "eval_recall": 0.6544074722708698,
+      "eval_runtime": 12.5601,
+      "eval_samples_per_second": 231.447,
+      "eval_steps_per_second": 28.981,
+      "step": 364
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.6608187134502928e-05,
+      "loss": 0.0262,
+      "step": 728
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9977715877437325,
+      "eval_f1": 0.9390029325513196,
+      "eval_loss": 0.008390289731323719,
+      "eval_precision": 0.943429581614614,
+      "eval_recall": 0.9346176298890835,
+      "eval_runtime": 12.5029,
+      "eval_samples_per_second": 232.507,
+      "eval_steps_per_second": 29.113,
+      "step": 728
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.3304093567251464e-05,
+      "loss": 0.0102,
+      "step": 1092
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9990464966788086,
+      "eval_f1": 0.9741654571843252,
+      "eval_loss": 0.0033252816647291183,
+      "eval_precision": 0.9688221709006929,
+      "eval_recall": 0.9795680093403386,
+      "eval_runtime": 12.4462,
+      "eval_samples_per_second": 233.565,
+      "eval_steps_per_second": 29.246,
+      "step": 1092
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.0046,
+      "step": 1456
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9995500321405614,
+      "eval_f1": 0.9878331402085747,
+      "eval_loss": 0.0015423308359459043,
+      "eval_precision": 0.980448533640023,
+      "eval_recall": 0.9953298307063632,
+      "eval_runtime": 12.5941,
+      "eval_samples_per_second": 230.823,
+      "eval_steps_per_second": 28.902,
+      "step": 1456
+    },
+    {
+      "epoch": 4.0,
+      "step": 1456,
+      "total_flos": 613160172693882.0,
+      "train_loss": 0.032722131645941475,
+      "train_runtime": 391.1103,
+      "train_samples_per_second": 29.731,
+      "train_steps_per_second": 3.723
+    }
+  ],
+  "max_steps": 1456,
+  "num_train_epochs": 4,
+  "total_flos": 613160172693882.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db694375f124bbb1c393afb707c7c4d3a138aa21cb4010acc9c4fe6639410467
+size 3311