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

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 sha256:7770e49062bba31693dbbb616439f80d01e7b76548e3dd5c142310abce735ee0
+size 2235515434

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": 0.9588719153936546,
+  "best_model_checkpoint": "experiments_results/cometa/outputs/xlm-roberta-large-output/cometa_8_0.01_0.00002_02-26-24_12-34/checkpoint-1452",
+  "epoch": 3.998624484181568,
+  "global_step": 1452,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.596774193548387e-05,
+      "loss": 0.1244,
+      "step": 363
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.988247268052282,
+      "eval_f1": 0.6509704104358893,
+      "eval_loss": 0.03377820923924446,
+      "eval_precision": 0.7153846153846154,
+      "eval_recall": 0.5971978984238179,
+      "eval_runtime": 18.9255,
+      "eval_samples_per_second": 153.602,
+      "eval_steps_per_second": 19.233,
+      "step": 363
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.0645161290322582e-05,
+      "loss": 0.0355,
+      "step": 726
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9933040497107349,
+      "eval_f1": 0.7906197654941373,
+      "eval_loss": 0.018763022497296333,
+      "eval_precision": 0.9276729559748428,
+      "eval_recall": 0.688849970811442,
+      "eval_runtime": 18.9192,
+      "eval_samples_per_second": 153.653,
+      "eval_steps_per_second": 19.24,
+      "step": 726
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.322580645161291e-06,
+      "loss": 0.0196,
+      "step": 1089
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9973966145275337,
+      "eval_f1": 0.9279573080343908,
+      "eval_loss": 0.00810301024466753,
+      "eval_precision": 0.9427710843373494,
+      "eval_recall": 0.9136018680677175,
+      "eval_runtime": 19.0179,
+      "eval_samples_per_second": 152.856,
+      "eval_steps_per_second": 19.14,
+      "step": 1089
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.0111,
+      "step": 1452
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9985001071352047,
+      "eval_f1": 0.9588719153936546,
+      "eval_loss": 0.005104937590658665,
+      "eval_precision": 0.9651094027202839,
+      "eval_recall": 0.9527145359019265,
+      "eval_runtime": 18.9209,
+      "eval_samples_per_second": 153.64,
+      "eval_steps_per_second": 19.238,
+      "step": 1452
+    },
+    {
+      "epoch": 4.0,
+      "step": 1452,
+      "total_flos": 1523924460800142.0,
+      "train_loss": 0.047672507848293,
+      "train_runtime": 706.4241,
+      "train_samples_per_second": 16.46,
+      "train_steps_per_second": 2.055
+    }
+  ],
+  "max_steps": 1452,
+  "num_train_epochs": 4,
+  "total_flos": 1523924460800142.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09fca7ef623fdd402e649a8e264b1525380042e0c81838ec82110a8c81b896e0
+size 3832