First model commit

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.0",
+  "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:d3584aedc331f9ca0e29d68986c1ef7b4a9482a37fe4c5d743eff2efd0cf7c8c
+size 1109929655

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4b5e0f6c2b4ecb027fd7533355563f7ed12410849fb90737be2a5280473180
+size 14657

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab02334ac3449c8dd78cf9f63524387bf84b06577fceaf9975bb5a97251feaf
+size 623

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_metric": 0.06587601453065872,
+  "best_model_checkpoint": "test-ner/checkpoint-2636",
+  "epoch": 4.0,
+  "global_step": 5272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.241274658573596e-06,
+      "loss": 0.2967,
+      "step": 500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.482549317147192e-06,
+      "loss": 0.0903,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9800172512938471,
+      "eval_f1": 0.8510216941218831,
+      "eval_loss": 0.07860440760850906,
+      "eval_precision": 0.8489583333333334,
+      "eval_recall": 0.8530951091860675,
+      "eval_runtime": 11.6301,
+      "eval_samples_per_second": 249.008,
+      "step": 1318
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.72382397572079e-06,
+      "loss": 0.0695,
+      "step": 1500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 6.965098634294386e-06,
+      "loss": 0.0487,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.206373292867982e-06,
+      "loss": 0.0521,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9845816561242093,
+      "eval_f1": 0.8887689955939214,
+      "eval_loss": 0.06587601453065872,
+      "eval_precision": 0.885663082437276,
+      "eval_recall": 0.8918967695361848,
+      "eval_runtime": 11.691,
+      "eval_samples_per_second": 247.711,
+      "step": 2636
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 5.447647951441578e-06,
+      "loss": 0.0388,
+      "step": 3000
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 4.688922610015174e-06,
+      "loss": 0.0344,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9849949683726279,
+      "eval_f1": 0.8925949424453912,
+      "eval_loss": 0.06827788800001144,
+      "eval_precision": 0.8965768390386016,
+      "eval_recall": 0.8886482584371053,
+      "eval_runtime": 11.7404,
+      "eval_samples_per_second": 246.67,
+      "step": 3954
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 3.930197268588772e-06,
+      "loss": 0.0297,
+      "step": 4000
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 3.1714719271623673e-06,
+      "loss": 0.0255,
+      "step": 4500
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 2.4127465857359637e-06,
+      "loss": 0.0235,
+      "step": 5000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9865943070730305,
+      "eval_f1": 0.904637078550122,
+      "eval_loss": 0.06835205852985382,
+      "eval_precision": 0.90619340818544,
+      "eval_recall": 0.9030860855441256,
+      "eval_runtime": 11.7952,
+      "eval_samples_per_second": 245.524,
+      "step": 5272
+    }
+  ],
+  "max_steps": 6590,
+  "num_train_epochs": 5,
+  "total_flos": 1452761017373610.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19dd6bfd2e3594dda61f7057f2b669c453ad3eb593ab2a50595fcdfc7be89262
+size 2415