adding model finetuned on POS

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9839718066450924,
+    "eval_f1": 0.9833950734391069,
+    "eval_loss": 0.05716780200600624,
+    "eval_precision": 0.9829141716566866,
+    "eval_recall": 0.9838764460250544,
+    "eval_runtime": 11.7694,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 140.534,
+    "eval_steps_per_second": 8.836,
+    "train_loss": 0.05827242064409416,
+    "train_runtime": 5244.9021,
+    "train_samples": 14305,
+    "train_samples_per_second": 10.91,
+    "train_steps_per_second": 0.683
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "CenIA/albert_xxlarge_spanish",
+  "architectures": [
+    "AlbertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "finetuning_task": "pos",
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 4096,
+  "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": 0.01,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "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-12,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 64,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9839718066450924,
+    "eval_f1": 0.9833950734391069,
+    "eval_loss": 0.05716780200600624,
+    "eval_precision": 0.9829141716566866,
+    "eval_recall": 0.9838764460250544,
+    "eval_runtime": 11.7694,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 140.534,
+    "eval_steps_per_second": 8.836
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24bd05067ad36d961a0f3b5fe3dd2342446c843c5924ae870591f8989e41e56c
+size 824078295

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "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": "CenIA/albert_xxlarge_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.05827242064409416,
+    "train_runtime": 5244.9021,
+    "train_samples": 14305,
+    "train_samples_per_second": 10.91,
+    "train_steps_per_second": 0.683
+}

trainer_state.json

@@ -0,0 +1,271 @@
+{
+  "best_metric": 0.05716780200600624,
+  "best_model_checkpoint": "/data/jcanete/all_results/pos/albeto_xxlarge/epochs_4_bs_16_lr_5e-6/checkpoint-1800",
+  "epoch": 4.0,
+  "global_step": 3580,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.9740770234323376,
+      "eval_f1": 0.9703136222169021,
+      "eval_loss": 0.09671590477228165,
+      "eval_precision": 0.9689025240552224,
+      "eval_recall": 0.9717288365866816,
+      "eval_runtime": 12.1146,
+      "eval_samples_per_second": 136.529,
+      "eval_steps_per_second": 8.585,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.978109486453974,
+      "eval_f1": 0.9763370891925068,
+      "eval_loss": 0.08312373608350754,
+      "eval_precision": 0.9753928372018824,
+      "eval_recall": 0.9772831711654113,
+      "eval_runtime": 12.0635,
+      "eval_samples_per_second": 137.107,
+      "eval_steps_per_second": 8.621,
+      "step": 400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.305865921787709e-06,
+      "loss": 0.2346,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9802951491841887,
+      "eval_f1": 0.9781281181400918,
+      "eval_loss": 0.06705235689878464,
+      "eval_precision": 0.9769778149853495,
+      "eval_recall": 0.979281133244091,
+      "eval_runtime": 12.0607,
+      "eval_samples_per_second": 137.14,
+      "eval_steps_per_second": 8.623,
+      "step": 600
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.9816167126954812,
+      "eval_f1": 0.980212056468521,
+      "eval_loss": 0.06424280256032944,
+      "eval_precision": 0.9796252319849933,
+      "eval_recall": 0.9807995844238876,
+      "eval_runtime": 12.0651,
+      "eval_samples_per_second": 137.09,
+      "eval_steps_per_second": 8.62,
+      "step": 800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.607541899441341e-06,
+      "loss": 0.0581,
+      "step": 1000
+    },
+    {
+      "epoch": 1.12,
+      "eval_accuracy": 0.9821419494756104,
+      "eval_f1": 0.9813241767565355,
+      "eval_loss": 0.06397537887096405,
+      "eval_precision": 0.9805313971116253,
+      "eval_recall": 0.9821182393958162,
+      "eval_runtime": 12.0587,
+      "eval_samples_per_second": 137.163,
+      "eval_steps_per_second": 8.624,
+      "step": 1000
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.982734958743498,
+      "eval_f1": 0.9817945902784708,
+      "eval_loss": 0.06401154398918152,
+      "eval_precision": 0.9809330062426455,
+      "eval_recall": 0.9826576891570598,
+      "eval_runtime": 12.05,
+      "eval_samples_per_second": 137.262,
+      "eval_steps_per_second": 8.631,
+      "step": 1200
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy": 0.9834635129869029,
+      "eval_f1": 0.982266245955985,
+      "eval_loss": 0.05947747826576233,
+      "eval_precision": 0.9818152783599816,
+      "eval_recall": 0.9827176280194202,
+      "eval_runtime": 12.0881,
+      "eval_samples_per_second": 136.829,
+      "eval_steps_per_second": 8.604,
+      "step": 1400
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.9092178770949727e-06,
+      "loss": 0.04,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "eval_accuracy": 0.9830229918164721,
+      "eval_f1": 0.982217698479224,
+      "eval_loss": 0.05940423533320427,
+      "eval_precision": 0.9811407268595124,
+      "eval_recall": 0.9832970370222374,
+      "eval_runtime": 12.0517,
+      "eval_samples_per_second": 137.242,
+      "eval_steps_per_second": 8.629,
+      "step": 1600
+    },
+    {
+      "epoch": 2.01,
+      "eval_accuracy": 0.9839718066450924,
+      "eval_f1": 0.9833950734391069,
+      "eval_loss": 0.05716780200600624,
+      "eval_precision": 0.9829141716566866,
+      "eval_recall": 0.9838764460250544,
+      "eval_runtime": 12.0638,
+      "eval_samples_per_second": 137.105,
+      "eval_steps_per_second": 8.621,
+      "step": 1800
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 2.2108938547486037e-06,
+      "loss": 0.0327,
+      "step": 2000
+    },
+    {
+      "epoch": 2.23,
+      "eval_accuracy": 0.983700716694058,
+      "eval_f1": 0.9826579207475964,
+      "eval_loss": 0.06271136552095413,
+      "eval_precision": 0.9820794252644183,
+      "eval_recall": 0.9832370981598769,
+      "eval_runtime": 12.0524,
+      "eval_samples_per_second": 137.234,
+      "eval_steps_per_second": 8.629,
+      "step": 2000
+    },
+    {
+      "epoch": 2.46,
+      "eval_accuracy": 0.9840734653767303,
+      "eval_f1": 0.9836376523674989,
+      "eval_loss": 0.06178496032953262,
+      "eval_precision": 0.982980166806337,
+      "eval_recall": 0.9842960180615772,
+      "eval_runtime": 12.0504,
+      "eval_samples_per_second": 137.257,
+      "eval_steps_per_second": 8.63,
+      "step": 2200
+    },
+    {
+      "epoch": 2.68,
+      "eval_accuracy": 0.9839887497670321,
+      "eval_f1": 0.983732286767129,
+      "eval_loss": 0.0652877539396286,
+      "eval_precision": 0.9833885716567504,
+      "eval_recall": 0.9840762422329224,
+      "eval_runtime": 12.0582,
+      "eval_samples_per_second": 137.168,
+      "eval_steps_per_second": 8.625,
+      "step": 2400
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.5125698324022347e-06,
+      "loss": 0.022,
+      "step": 2500
+    },
+    {
+      "epoch": 2.91,
+      "eval_accuracy": 0.9843445553277647,
+      "eval_f1": 0.9838023527532006,
+      "eval_loss": 0.061138641089200974,
+      "eval_precision": 0.9834487990895842,
+      "eval_recall": 0.9841561607160696,
+      "eval_runtime": 12.0686,
+      "eval_samples_per_second": 137.05,
+      "eval_steps_per_second": 8.617,
+      "step": 2600
+    },
+    {
+      "epoch": 3.13,
+      "eval_accuracy": 0.984378441571644,
+      "eval_f1": 0.9841013042523019,
+      "eval_loss": 0.06497478485107422,
+      "eval_precision": 0.9837869137232195,
+      "eval_recall": 0.984415895786298,
+      "eval_runtime": 12.0336,
+      "eval_samples_per_second": 137.449,
+      "eval_steps_per_second": 8.642,
+      "step": 2800
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 8.142458100558661e-07,
+      "loss": 0.0161,
+      "step": 3000
+    },
+    {
+      "epoch": 3.35,
+      "eval_accuracy": 0.9844631571813423,
+      "eval_f1": 0.9838933546357782,
+      "eval_loss": 0.06659159064292908,
+      "eval_precision": 0.9834710743801653,
+      "eval_recall": 0.984315997682364,
+      "eval_runtime": 12.058,
+      "eval_samples_per_second": 137.17,
+      "eval_steps_per_second": 8.625,
+      "step": 3000
+    },
+    {
+      "epoch": 3.58,
+      "eval_accuracy": 0.9840056928889718,
+      "eval_f1": 0.983372447196285,
+      "eval_loss": 0.06790520250797272,
+      "eval_precision": 0.9830484785560258,
+      "eval_recall": 0.9836966294379733,
+      "eval_runtime": 12.0261,
+      "eval_samples_per_second": 137.534,
+      "eval_steps_per_second": 8.648,
+      "step": 3200
+    },
+    {
+      "epoch": 3.8,
+      "eval_accuracy": 0.9842767828400061,
+      "eval_f1": 0.9837931757586651,
+      "eval_loss": 0.06859102845191956,
+      "eval_precision": 0.9833905613670846,
+      "eval_recall": 0.9841961199576432,
+      "eval_runtime": 12.0273,
+      "eval_samples_per_second": 137.521,
+      "eval_steps_per_second": 8.647,
+      "step": 3400
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.1592178770949721e-07,
+      "loss": 0.012,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "step": 3580,
+      "total_flos": 5364557434522752.0,
+      "train_loss": 0.05827242064409416,
+      "train_runtime": 5244.9021,
+      "train_samples_per_second": 10.91,
+      "train_steps_per_second": 0.683
+    }
+  ],
+  "max_steps": 3580,
+  "num_train_epochs": 4,
+  "total_flos": 5364557434522752.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211fc83f4ac4107250cd13c933f937281918a6fa555449d8858952b06da464f0
+size 2863