upload model

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "bsc/roberta-base-ca-cased",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NOUN",
+    "1": "PUNCT",
+    "2": "ADP",
+    "3": "NUM",
+    "4": "SYM",
+    "5": "SCONJ",
+    "6": "ADJ",
+    "7": "PART",
+    "8": "DET",
+    "9": "CCONJ",
+    "10": "PROPN",
+    "11": "PRON",
+    "12": "X",
+    "13": "_",
+    "14": "ADV",
+    "15": "INTJ",
+    "16": "VERB",
+    "17": "AUX"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NOUN": 0,
+    "PUNCT": 1,
+    "PROPN": 10,
+    "PRON": 11,
+    "X": 12,
+    "_": 13,
+    "ADV": 14,
+    "INTJ": 15,
+    "VERB": 16,
+    "AUX": 17,
+    "ADP": 2,
+    "NUM": 3,
+    "SYM": 4,
+    "SCONJ": 5,
+    "ADJ": 6,
+    "PART": 7,
+    "DET": 8,
+    "CCONJ": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3ef85b9bd9c626ef882eabb3f68e19f65d88416f8187ca0fed5e17724f34a4
+size 501693261

special_tokens_map.json

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": 0.9909600298841987,
+  "best_model_checkpoint": "/home/shared/dt01/temutauro/ccasimiro/berta/src/finetuning/pos/roberta-base-ca-cased-pos/checkpoint-1230",
+  "epoch": 9.99878197320341,
+  "global_step": 4100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9902717208990272,
+      "eval_f1": 0.9884402778815269,
+      "eval_loss": 0.04564520716667175,
+      "eval_precision": 0.9881081282903335,
+      "eval_recall": 0.9887726508499907,
+      "eval_runtime": 13.2852,
+      "eval_samples_per_second": 128.639,
+      "step": 410
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 0.1804,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9918077649676018,
+      "eval_f1": 0.9899899152130878,
+      "eval_loss": 0.036869727075099945,
+      "eval_precision": 0.9896941861767671,
+      "eval_recall": 0.9902858210349337,
+      "eval_runtime": 13.3317,
+      "eval_samples_per_second": 128.191,
+      "step": 820
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 3.780487804878049e-05,
+      "loss": 0.0303,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.992355091015025,
+      "eval_f1": 0.9909600298841987,
+      "eval_loss": 0.03579937666654587,
+      "eval_precision": 0.9907749766573296,
+      "eval_recall": 0.9911451522510741,
+      "eval_runtime": 13.2482,
+      "eval_samples_per_second": 128.999,
+      "step": 1230
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 3.170731707317073e-05,
+      "loss": 0.0194,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9921079115097371,
+      "eval_f1": 0.9907175675170894,
+      "eval_loss": 0.037922825664281845,
+      "eval_precision": 0.9904955745602569,
+      "eval_recall": 0.9909396600037362,
+      "eval_runtime": 13.1871,
+      "eval_samples_per_second": 129.596,
+      "step": 1640
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 2.5609756097560977e-05,
+      "loss": 0.0133,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.992231501262381,
+      "eval_f1": 0.9908294577986965,
+      "eval_loss": 0.03801530599594116,
+      "eval_precision": 0.9906259336719451,
+      "eval_recall": 0.991033065570708,
+      "eval_runtime": 13.3822,
+      "eval_samples_per_second": 127.707,
+      "step": 2050
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9916841752149579,
+      "eval_f1": 0.9903335170120761,
+      "eval_loss": 0.04094540327787399,
+      "eval_precision": 0.9902317849872061,
+      "eval_recall": 0.9904352699420885,
+      "eval_runtime": 13.2046,
+      "eval_samples_per_second": 129.424,
+      "step": 2460
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 0.0085,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9918430763255001,
+      "eval_f1": 0.9904548426263192,
+      "eval_loss": 0.04267619550228119,
+      "eval_precision": 0.9903623459096003,
+      "eval_recall": 0.9905473566224547,
+      "eval_runtime": 13.3294,
+      "eval_samples_per_second": 128.212,
+      "step": 2870
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 1.3414634146341466e-05,
+      "loss": 0.0059,
+      "step": 3000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9922668126202793,
+      "eval_f1": 0.9909512826019965,
+      "eval_loss": 0.04542930796742439,
+      "eval_precision": 0.9907014956028157,
+      "eval_recall": 0.9912011955912572,
+      "eval_runtime": 13.2987,
+      "eval_samples_per_second": 128.508,
+      "step": 3280
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 7.317073170731707e-06,
+      "loss": 0.0037,
+      "step": 3500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.991966666078144,
+      "eval_f1": 0.9906329090280827,
+      "eval_loss": 0.04698851332068443,
+      "eval_precision": 0.9904756568995462,
+      "eval_recall": 0.9907902110965814,
+      "eval_runtime": 13.2254,
+      "eval_samples_per_second": 129.221,
+      "step": 3690
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 1.2195121951219514e-06,
+      "loss": 0.0028,
+      "step": 4000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9919843217570932,
+      "eval_f1": 0.9906423354937522,
+      "eval_loss": 0.04776829481124878,
+      "eval_precision": 0.9904758347650706,
+      "eval_recall": 0.9908088922099757,
+      "eval_runtime": 13.2102,
+      "eval_samples_per_second": 129.37,
+      "step": 4100
+    },
+    {
+      "epoch": 10.0,
+      "step": 4100,
+      "total_flos": 0,
+      "train_runtime": 3867.6486,
+      "train_samples_per_second": 1.06
+    }
+  ],
+  "max_steps": 4100,
+  "num_train_epochs": 10,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4ca07a4cfb95ccbc90161bc8bd5268a9e427fc9d3086dcd7ed5949b6eb26c5
+size 2479