Upload 12 files

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9905438520216592,
+    "eval_f1": 0.9003506721215664,
+    "eval_loss": 0.04321206733584404,
+    "eval_mem_cpu_alloc_delta": 149028864,
+    "eval_mem_cpu_peaked_delta": 9793536,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 314081280,
+    "eval_precision": 0.8971173444627778,
+    "eval_recall": 0.9036073907517841,
+    "eval_runtime": 34.5441,
+    "eval_samples": 7550,
+    "eval_samples_per_second": 218.561,
+    "init_mem_cpu_alloc_delta": -68857856,
+    "init_mem_cpu_peaked_delta": 154255360,
+    "init_mem_gpu_alloc_delta": 497570816,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 2823634944,
+    "train_mem_cpu_peaked_delta": 164388864,
+    "train_mem_gpu_alloc_delta": 1508407296,
+    "train_mem_gpu_peaked_delta": 10039297024,
+    "train_runtime": 1076.7664,
+    "train_samples": 22648,
+    "train_samples_per_second": 3.288
+}

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "roberta-base-bne",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOC",
+    "1": "B-ORG",
+    "2": "B-OTH",
+    "3": "B-PER",
+    "4": "E-LOC",
+    "5": "E-ORG",
+    "6": "E-OTH",
+    "7": "E-PER",
+    "8": "I-LOC",
+    "9": "I-ORG",
+    "10": "I-OTH",
+    "11": "I-PER",
+    "12": "O",
+    "13": "S-LOC",
+    "14": "S-ORG",
+    "15": "S-OTH",
+    "16": "S-PER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 0,
+    "B-ORG": 1,
+    "B-OTH": 2,
+    "B-PER": 3,
+    "E-LOC": 4,
+    "E-ORG": 5,
+    "E-OTH": 6,
+    "E-PER": 7,
+    "I-LOC": 8,
+    "I-ORG": 9,
+    "I-OTH": 10,
+    "I-PER": 11,
+    "O": 12,
+    "S-LOC": 13,
+    "S-ORG": 14,
+    "S-OTH": 15,
+    "S-PER": 16
+
+  },
+  "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": 50262
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9905438520216592,
+    "eval_f1": 0.9003506721215664,
+    "eval_loss": 0.04321206733584404,
+    "eval_mem_cpu_alloc_delta": 149028864,
+    "eval_mem_cpu_peaked_delta": 9793536,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 314081280,
+    "eval_precision": 0.8971173444627778,
+    "eval_recall": 0.9036073907517841,
+    "eval_runtime": 34.5441,
+    "eval_samples": 7550,
+    "eval_samples_per_second": 218.561
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2322a56610f6b0151e9380411b7ca1b8c5883e983a6dc1e4ecb1adf2cfcd6a66
+size 496347953

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, "model_max_length": 512, "name_or_path": "roberta-base-bne", "special_tokens_map_file": null, "tokenizer_class": "RobertaTokenizer", "trim_offsets": true}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "init_mem_cpu_alloc_delta": -68857856,
+    "init_mem_cpu_peaked_delta": 154255360,
+    "init_mem_gpu_alloc_delta": 497570816,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 2823634944,
+    "train_mem_cpu_peaked_delta": 164388864,
+    "train_mem_gpu_alloc_delta": 1508407296,
+    "train_mem_gpu_peaked_delta": 10039297024,
+    "train_runtime": 1076.7664,
+    "train_samples": 22648,
+    "train_samples_per_second": 3.288
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": 0.9003506721215664,
+  "best_model_checkpoint": "output/roberta-base-bne-capitel-iris-ner/iris_16_0.00005_07-17-23_22-27/checkpoint-3540",
+  "epoch": 5.0,
+  "global_step": 3540,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0969,
+      "step": 708
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9882810956088692,
+      "eval_f1": 0.8684808352264488,
+      "eval_loss": 0.04088732972741127,
+      "eval_precision": 0.8588910133843213,
+      "eval_recall": 0.8782872226024049,
+      "eval_runtime": 34.6042,
+      "eval_samples_per_second": 218.182,
+      "step": 708
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.0253,
+      "step": 1416
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9890666376823051,
+      "eval_f1": 0.8800116352353711,
+      "eval_loss": 0.03929711878299713,
+      "eval_precision": 0.8728601654164262,
+      "eval_recall": 0.8872812591651188,
+      "eval_runtime": 34.2725,
+      "eval_samples_per_second": 220.293,
+      "step": 1416
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0117,
+      "step": 2124
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9898768823366665,
+      "eval_f1": 0.892319680514294,
+      "eval_loss": 0.03888658434152603,
+      "eval_precision": 0.8890722049689441,
+      "eval_recall": 0.8955909668589305,
+      "eval_runtime": 34.6426,
+      "eval_samples_per_second": 217.94,
+      "step": 2124
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0054,
+      "step": 2832
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9904549227303269,
+      "eval_f1": 0.8978559968885217,
+      "eval_loss": 0.040431126952171326,
+      "eval_precision": 0.893036750483559,
+      "eval_recall": 0.9027275393489099,
+      "eval_runtime": 34.4446,
+      "eval_samples_per_second": 219.192,
+      "step": 2832
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.0026,
+      "step": 3540
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9905438520216592,
+      "eval_f1": 0.9003506721215664,
+      "eval_loss": 0.04321206733584404,
+      "eval_precision": 0.8971173444627778,
+      "eval_recall": 0.9036073907517841,
+      "eval_runtime": 34.2514,
+      "eval_samples_per_second": 220.429,
+      "step": 3540
+    },
+    {
+      "epoch": 5.0,
+      "step": 3540,
+      "total_flos": 0,
+      "train_runtime": 1076.7664,
+      "train_samples_per_second": 3.288
+    }
+  ],
+  "max_steps": 3540,
+  "num_train_epochs": 5,
+  "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 sha256:372826fd22322afeabb836f01b27229bb024f143adf407e671ef9698d56f638d
+size 2543