adding model finetuned on NER

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9778161165226419,
+    "eval_f1": 0.8677048922447697,
+    "eval_loss": 0.08214916288852692,
+    "eval_precision": 0.8679779701022816,
+    "eval_recall": 0.8674319861613461,
+    "eval_runtime": 2.0782,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 921.958,
+    "eval_steps_per_second": 28.871,
+    "train_loss": 0.07351639238810631,
+    "train_runtime": 113.4173,
+    "train_samples": 8324,
+    "train_samples_per_second": 293.571,
+    "train_steps_per_second": 9.205
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9778161165226419,
+    "eval_f1": 0.8677048922447697,
+    "eval_loss": 0.08214916288852692,
+    "eval_precision": 0.8679779701022816,
+    "eval_recall": 0.8674319861613461,
+    "eval_runtime": 2.0782,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 921.958,
+    "eval_steps_per_second": 28.871
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4abb77da5e922e6ff3e1c0d0fab6443a014628046f0ce9b7141aa51cf022ee
+size 496323313

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"}, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "PlanTL-GOB-ES/roberta-base-bne", "do_lower_case": false, "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.07351639238810631,
+    "train_runtime": 113.4173,
+    "train_samples": 8324,
+    "train_samples_per_second": 293.571,
+    "train_steps_per_second": 9.205
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.08214916288852692,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/ner/roberta_base_bne/epochs_4_bs_32_lr_3e-5/checkpoint-500",
+  "epoch": 4.0,
+  "global_step": 1044,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.38,
+      "eval_accuracy": 0.9629454334483496,
+      "eval_f1": 0.7416711342574863,
+      "eval_loss": 0.1347309798002243,
+      "eval_precision": 0.7229023589131084,
+      "eval_recall": 0.7614404780625884,
+      "eval_runtime": 2.0941,
+      "eval_samples_per_second": 914.935,
+      "eval_steps_per_second": 28.651,
+      "step": 100
+    },
+    {
+      "epoch": 0.77,
+      "eval_accuracy": 0.9751748144981526,
+      "eval_f1": 0.846393519239757,
+      "eval_loss": 0.09219810366630554,
+      "eval_precision": 0.8385553326130576,
+      "eval_recall": 0.8543796194370183,
+      "eval_runtime": 2.0125,
+      "eval_samples_per_second": 952.045,
+      "eval_steps_per_second": 29.814,
+      "step": 200
+    },
+    {
+      "epoch": 1.15,
+      "eval_accuracy": 0.9743656294848698,
+      "eval_f1": 0.8412611054328171,
+      "eval_loss": 0.09414725750684738,
+      "eval_precision": 0.8411949685534591,
+      "eval_recall": 0.8413272527126907,
+      "eval_runtime": 2.0091,
+      "eval_samples_per_second": 953.677,
+      "eval_steps_per_second": 29.865,
+      "step": 300
+    },
+    {
+      "epoch": 1.53,
+      "eval_accuracy": 0.9758313230938349,
+      "eval_f1": 0.854766575127501,
+      "eval_loss": 0.08752118051052094,
+      "eval_precision": 0.8529595991230817,
+      "eval_recall": 0.8565812234628086,
+      "eval_runtime": 2.0067,
+      "eval_samples_per_second": 954.82,
+      "eval_steps_per_second": 29.9,
+      "step": 400
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.5689655172413794e-05,
+      "loss": 0.1335,
+      "step": 500
+    },
+    {
+      "epoch": 1.92,
+      "eval_accuracy": 0.9778161165226419,
+      "eval_f1": 0.8677048922447697,
+      "eval_loss": 0.08214916288852692,
+      "eval_precision": 0.8679779701022816,
+      "eval_recall": 0.8674319861613461,
+      "eval_runtime": 2.0137,
+      "eval_samples_per_second": 951.47,
+      "eval_steps_per_second": 29.796,
+      "step": 500
+    },
+    {
+      "epoch": 2.3,
+      "eval_accuracy": 0.9771443402851996,
+      "eval_f1": 0.859778020947319,
+      "eval_loss": 0.0927521213889122,
+      "eval_precision": 0.8547008547008547,
+      "eval_recall": 0.8649158672747287,
+      "eval_runtime": 2.07,
+      "eval_samples_per_second": 925.61,
+      "eval_steps_per_second": 28.986,
+      "step": 600
+    },
+    {
+      "epoch": 2.68,
+      "eval_accuracy": 0.9763504229136768,
+      "eval_f1": 0.8577878103837472,
+      "eval_loss": 0.092233806848526,
+      "eval_precision": 0.8492601726263872,
+      "eval_recall": 0.8664884415788646,
+      "eval_runtime": 2.0104,
+      "eval_samples_per_second": 953.047,
+      "eval_steps_per_second": 29.845,
+      "step": 700
+    },
+    {
+      "epoch": 3.07,
+      "eval_accuracy": 0.9773428196280802,
+      "eval_f1": 0.8647045046451715,
+      "eval_loss": 0.09490890055894852,
+      "eval_precision": 0.8586046511627907,
+      "eval_recall": 0.8708916496304451,
+      "eval_runtime": 1.9928,
+      "eval_samples_per_second": 961.47,
+      "eval_steps_per_second": 30.109,
+      "step": 800
+    },
+    {
+      "epoch": 3.45,
+      "eval_accuracy": 0.9767321139576781,
+      "eval_f1": 0.859104384459354,
+      "eval_loss": 0.09667886048555374,
+      "eval_precision": 0.852453940238427,
+      "eval_recall": 0.8658594118572103,
+      "eval_runtime": 2.002,
+      "eval_samples_per_second": 957.043,
+      "eval_steps_per_second": 29.97,
+      "step": 900
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.32183908045977e-06,
+      "loss": 0.0189,
+      "step": 1000
+    },
+    {
+      "epoch": 3.83,
+      "eval_accuracy": 0.977556566612721,
+      "eval_f1": 0.8655850772004076,
+      "eval_loss": 0.09368374198675156,
+      "eval_precision": 0.8628125,
+      "eval_recall": 0.8683755307438277,
+      "eval_runtime": 2.004,
+      "eval_samples_per_second": 956.073,
+      "eval_steps_per_second": 29.94,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "step": 1044,
+      "total_flos": 1723769471413440.0,
+      "train_loss": 0.07351639238810631,
+      "train_runtime": 113.4173,
+      "train_samples_per_second": 293.571,
+      "train_steps_per_second": 9.205
+    }
+  ],
+  "max_steps": 1044,
+  "num_train_epochs": 4,
+  "total_flos": 1723769471413440.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f8f9a5fef1daafc1356cf98f288ddd52b1389b48fdd675f7af45f39da88b34
+size 2991