Upload 13 files

added_tokens.json

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

all_results.json

@@ -0,0 +1,27 @@
+{
+    "epoch": 3.18,
+    "eval_f1": 0.993526599442064,
+    "eval_f1_0": 0.9979671388907684,
+    "eval_f1_1": 0.9974921281221278,
+    "eval_f1_2": 0.9797800483751775,
+    "eval_f1_3": 0.9988670823801823,
+    "eval_loss": 0.013590204529464245,
+    "eval_runtime": 58.1458,
+    "eval_samples": 11868,
+    "eval_samples_per_second": 204.107,
+    "eval_steps_per_second": 0.413,
+    "test_f1": 0.22024020311647546,
+    "test_f1_0": 0.8809608124659019,
+    "test_f1_1": 0.0,
+    "test_f1_2": 0.0,
+    "test_f1_3": 0.0,
+    "test_loss": 2.4076662063598633,
+    "test_runtime": 2305.3492,
+    "test_samples_per_second": 206.564,
+    "test_steps_per_second": 0.404,
+    "train_loss": 0.03157895615913044,
+    "train_runtime": 7385.7528,
+    "train_samples": 106803,
+    "train_samples_per_second": 86.764,
+    "train_steps_per_second": 2.712
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "models/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",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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": "4.34.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "eval_f1": 0.993526599442064,
+    "eval_f1_0": 0.9979671388907684,
+    "eval_f1_1": 0.9974921281221278,
+    "eval_f1_2": 0.9797800483751775,
+    "eval_f1_3": 0.9988670823801823,
+    "eval_loss": 0.013590204529464245,
+    "eval_runtime": 58.1458,
+    "eval_samples": 11868,
+    "eval_samples_per_second": 204.107,
+    "eval_steps_per_second": 0.413
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49adcc22e20119554e7cac83782f3092caeb90850e424426ce8f78ea67fc3a66
+size 1736201005

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

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

test_results.json

@@ -0,0 +1,11 @@
+{
+    "test_f1": 0.22024020311647546,
+    "test_f1_0": 0.8809608124659019,
+    "test_f1_1": 0.0,
+    "test_f1_2": 0.0,
+    "test_f1_3": 0.0,
+    "test_loss": 2.4076662063598633,
+    "test_runtime": 2305.3492,
+    "test_samples_per_second": 206.564,
+    "test_steps_per_second": 0.404
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.18,
+    "train_loss": 0.03157895615913044,
+    "train_runtime": 7385.7528,
+    "train_samples": 106803,
+    "train_samples_per_second": 86.764,
+    "train_steps_per_second": 2.712
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c1739d87e4aec9d71e1146e5ff7c2d00c01cca44e721352277f77a65765c41
+size 4219