Upload 9 files

added_tokens.json

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

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "microsoft/deberta-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": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7937793929056bf9b426fee3e9fad168ee4577aa2c54f20d569511ac3c9b2817
+size 735407023

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-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": 0.7524875621890547,
+  "best_model_checkpoint": "./outputs/deberta-base-output/vua_metaphor_32_0.1_0.00005_03-21-23_21-55/checkpoint-906",
+  "epoch": 4.0,
+  "global_step": 1208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.9911894273127756e-05,
+      "loss": 0.1588,
+      "step": 302
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9615206305053314,
+      "eval_f1": 0.6345506345506345,
+      "eval_loss": 0.09228184819221497,
+      "eval_precision": 0.8226997985224983,
+      "eval_recall": 0.5164418212478921,
+      "eval_runtime": 7.3935,
+      "eval_samples_per_second": 325.962,
+      "eval_steps_per_second": 40.847,
+      "step": 302
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.6607929515418507e-05,
+      "loss": 0.0661,
+      "step": 604
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9673020807766779,
+      "eval_f1": 0.7279328341275245,
+      "eval_loss": 0.08415527641773224,
+      "eval_precision": 0.7882063882063882,
+      "eval_recall": 0.6762225969645869,
+      "eval_runtime": 7.0018,
+      "eval_samples_per_second": 344.196,
+      "eval_steps_per_second": 43.132,
+      "step": 604
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.3303964757709254e-05,
+      "loss": 0.0358,
+      "step": 906
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9674384357359077,
+      "eval_f1": 0.7524875621890547,
+      "eval_loss": 0.10287901014089584,
+      "eval_precision": 0.7402120717781403,
+      "eval_recall": 0.765177065767285,
+      "eval_runtime": 6.9543,
+      "eval_samples_per_second": 346.549,
+      "eval_steps_per_second": 43.426,
+      "step": 906
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.019,
+      "step": 1208
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.968229294499441,
+      "eval_f1": 0.738378621154278,
+      "eval_loss": 0.11687722057104111,
+      "eval_precision": 0.7900048053820279,
+      "eval_recall": 0.6930860033726813,
+      "eval_runtime": 6.91,
+      "eval_samples_per_second": 348.768,
+      "eval_steps_per_second": 43.704,
+      "step": 1208
+    },
+    {
+      "epoch": 4.0,
+      "step": 1208,
+      "total_flos": 1154456176071726.0,
+      "train_loss": 0.0699166256860392,
+      "train_runtime": 336.8243,
+      "train_samples_per_second": 114.398,
+      "train_steps_per_second": 3.586
+    }
+  ],
+  "max_steps": 1208,
+  "num_train_epochs": 4,
+  "total_flos": 1154456176071726.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a2103ef38478a8a6c086851619f910ff30f3ad50c31f20e0d3b5c830f056fb
+size 3311