Upload 8 files

.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

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554c5538acc9772548f6755c26e33b772b7b3abd67bdd22183199104eaf43eb0
+size 2235512177

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": 0.7399236317352567,
+  "best_model_checkpoint": "./outputs/xlm-roberta-large-output/vua_metaphor_32_0.1_0.00003_07-19-22_17-18/checkpoint-903",
+  "epoch": 3.998341625207297,
+  "global_step": 1204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.3952254641909816e-05,
+      "loss": 0.2302,
+      "step": 301
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9587389893370422,
+      "eval_f1": 0.6235381935804927,
+      "eval_loss": 0.1028517335653305,
+      "eval_precision": 0.7607771706132362,
+      "eval_recall": 0.5282462057335582,
+      "eval_runtime": 10.4111,
+      "eval_samples_per_second": 231.484,
+      "eval_steps_per_second": 29.008,
+      "step": 301
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.596816976127321e-05,
+      "loss": 0.0825,
+      "step": 602
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9657749052333033,
+      "eval_f1": 0.7058823529411765,
+      "eval_loss": 0.08832709491252899,
+      "eval_precision": 0.7947229551451187,
+      "eval_recall": 0.6349072512647554,
+      "eval_runtime": 10.4364,
+      "eval_samples_per_second": 230.922,
+      "eval_steps_per_second": 28.937,
+      "step": 602
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.984084880636604e-06,
+      "loss": 0.053,
+      "step": 903
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9665657639968366,
+      "eval_f1": 0.7399236317352567,
+      "eval_loss": 0.09772537648677826,
+      "eval_precision": 0.7446626814688301,
+      "eval_recall": 0.7352445193929174,
+      "eval_runtime": 10.4481,
+      "eval_samples_per_second": 230.664,
+      "eval_steps_per_second": 28.905,
+      "step": 903
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.0302,
+      "step": 1204
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9673838937522158,
+      "eval_f1": 0.7341040462427745,
+      "eval_loss": 0.11126415431499481,
+      "eval_precision": 0.7765757290686736,
+      "eval_recall": 0.6960370994940978,
+      "eval_runtime": 10.506,
+      "eval_samples_per_second": 229.394,
+      "eval_steps_per_second": 28.746,
+      "step": 1204
+    },
+    {
+      "epoch": 4.0,
+      "step": 1204,
+      "total_flos": 4407052490588292.0,
+      "train_loss": 0.0989648171041495,
+      "train_runtime": 907.5206,
+      "train_samples_per_second": 42.459,
+      "train_steps_per_second": 1.327
+    }
+  ],
+  "max_steps": 1204,
+  "num_train_epochs": 4,
+  "total_flos": 4407052490588292.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9bf497afbb89a829244609804a72cf2acc6b079da90fc77cf53eb4c66cfd685
+size 3311