adding model finetuned on POS

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.960938373337166,
+    "eval_f1": 0.951597772499551,
+    "eval_loss": 0.13029101490974426,
+    "eval_precision": 0.9506490398995034,
+    "eval_recall": 0.952548400631356,
+    "eval_runtime": 3.9206,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 421.871,
+    "eval_steps_per_second": 26.526,
+    "train_loss": 0.19050939762392524,
+    "train_runtime": 272.28,
+    "train_samples": 14305,
+    "train_samples_per_second": 105.076,
+    "train_steps_per_second": 6.574
+}

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-large-bne",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "pos",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "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",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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": 2.0,
+    "eval_accuracy": 0.960938373337166,
+    "eval_f1": 0.951597772499551,
+    "eval_loss": 0.13029101490974426,
+    "eval_precision": 0.9506490398995034,
+    "eval_recall": 0.952548400631356,
+    "eval_runtime": 3.9206,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 421.871,
+    "eval_steps_per_second": 26.526
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed444aa8d1a0a64f94273e2767e77dd14f7aea561ee0197d77d6551353abc74
+size 1417465521

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-large-bne", "do_lower_case": false, "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.19050939762392524,
+    "train_runtime": 272.28,
+    "train_samples": 14305,
+    "train_samples_per_second": 105.076,
+    "train_steps_per_second": 6.574
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": 0.13029101490974426,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/pos/roberta_large_bne/epochs_2_bs_16_lr_5e-5/checkpoint-1600",
+  "epoch": 2.0,
+  "global_step": 1790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.8726584582954056,
+      "eval_f1": 0.8425117528542645,
+      "eval_loss": 0.38713014125823975,
+      "eval_precision": 0.8330501357395363,
+      "eval_recall": 0.8521907654192723,
+      "eval_runtime": 3.9474,
+      "eval_samples_per_second": 419.014,
+      "eval_steps_per_second": 26.347,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.9134448010987081,
+      "eval_f1": 0.8921425085407516,
+      "eval_loss": 0.26501840353012085,
+      "eval_precision": 0.889493545183714,
+      "eval_recall": 0.8948072965575113,
+      "eval_runtime": 3.9579,
+      "eval_samples_per_second": 417.895,
+      "eval_steps_per_second": 26.276,
+      "step": 400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.608938547486034e-05,
+      "loss": 0.4031,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9339657292515051,
+      "eval_f1": 0.915745815140092,
+      "eval_loss": 0.20921829342842102,
+      "eval_precision": 0.9117647058823529,
+      "eval_recall": 0.9197618429202213,
+      "eval_runtime": 3.8819,
+      "eval_samples_per_second": 426.082,
+      "eval_steps_per_second": 26.791,
+      "step": 600
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.9399543269614654,
+      "eval_f1": 0.9255756947696724,
+      "eval_loss": 0.18737097084522247,
+      "eval_precision": 0.9232298334194728,
+      "eval_recall": 0.9279335078220216,
+      "eval_runtime": 3.8865,
+      "eval_samples_per_second": 425.58,
+      "eval_steps_per_second": 26.76,
+      "step": 800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.212290502793296e-05,
+      "loss": 0.1622,
+      "step": 1000
+    },
+    {
+      "epoch": 1.12,
+      "eval_accuracy": 0.9501908366470241,
+      "eval_f1": 0.9376133984647592,
+      "eval_loss": 0.16575469076633453,
+      "eval_precision": 0.935673212757914,
+      "eval_recall": 0.9395616471199376,
+      "eval_runtime": 3.8706,
+      "eval_samples_per_second": 427.321,
+      "eval_steps_per_second": 26.869,
+      "step": 1000
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.9536402689279612,
+      "eval_f1": 0.9416929400965798,
+      "eval_loss": 0.1559223085641861,
+      "eval_precision": 0.940510592502541,
+      "eval_recall": 0.942878264170546,
+      "eval_runtime": 3.799,
+      "eval_samples_per_second": 435.378,
+      "eval_steps_per_second": 27.376,
+      "step": 1200
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy": 0.9577604241524138,
+      "eval_f1": 0.9459559227001088,
+      "eval_loss": 0.13980740308761597,
+      "eval_precision": 0.9447212147782074,
+      "eval_recall": 0.9471938622604943,
+      "eval_runtime": 3.8091,
+      "eval_samples_per_second": 434.224,
+      "eval_steps_per_second": 27.303,
+      "step": 1400
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.156424581005587e-06,
+      "loss": 0.0793,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "eval_accuracy": 0.960938373337166,
+      "eval_f1": 0.951597772499551,
+      "eval_loss": 0.13029101490974426,
+      "eval_precision": 0.9506490398995034,
+      "eval_recall": 0.952548400631356,
+      "eval_runtime": 3.835,
+      "eval_samples_per_second": 431.293,
+      "eval_steps_per_second": 27.119,
+      "step": 1600
+    },
+    {
+      "epoch": 2.0,
+      "step": 1790,
+      "total_flos": 4231215425384640.0,
+      "train_loss": 0.19050939762392524,
+      "train_runtime": 272.28,
+      "train_samples_per_second": 105.076,
+      "train_steps_per_second": 6.574
+    }
+  ],
+  "max_steps": 1790,
+  "num_train_epochs": 2,
+  "total_flos": 4231215425384640.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2ec57283b8a6c6a45f412f9fb0f2f79ac7e8a38c01249b1f09454831ac3ebd
+size 2991