adding model finetuned on POS

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9801257179647922,
+    "eval_f1": 0.9793164031304904,
+    "eval_loss": 0.07265603542327881,
+    "eval_precision": 0.9785935162094763,
+    "eval_recall": 0.9800403588339893,
+    "eval_runtime": 3.5805,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 461.944,
+    "eval_steps_per_second": 29.046,
+    "train_loss": 0.1316441932870023,
+    "train_runtime": 1079.4521,
+    "train_samples": 14305,
+    "train_samples_per_second": 53.008,
+    "train_steps_per_second": 3.316
+}

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "CenIA/albert_large_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": 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,
+  "inner_group_num": 1,
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 16,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 24,
+  "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": 0.9801257179647922,
+    "eval_f1": 0.9793164031304904,
+    "eval_loss": 0.07265603542327881,
+    "eval_precision": 0.9785935162094763,
+    "eval_recall": 0.9800403588339893,
+    "eval_runtime": 3.5805,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 461.944,
+    "eval_steps_per_second": 29.046
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f39fa359a9ca41ca91e39934dda7f80852a40f8365103575fed72d25e609b3b
+size 67137495

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_large_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.1316441932870023,
+    "train_runtime": 1079.4521,
+    "train_samples": 14305,
+    "train_samples_per_second": 53.008,
+    "train_steps_per_second": 3.316
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.07265603542327881,
+  "best_model_checkpoint": "/data/jcanete/all_results/pos/albeto_large/epochs_4_bs_16_lr_5e-6/checkpoint-3300",
+  "epoch": 4.0,
+  "global_step": 3580,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.9613357957337219,
+      "eval_f1": 0.956240711001167,
+      "eval_loss": 0.15343289077281952,
+      "eval_precision": 0.9548025975060754,
+      "eval_recall": 0.957683163173563,
+      "eval_runtime": 3.7594,
+      "eval_samples_per_second": 439.96,
+      "eval_steps_per_second": 27.664,
+      "step": 300
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.305865921787709e-06,
+      "loss": 0.5366,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9719421900679419,
+      "eval_f1": 0.9686646055649745,
+      "eval_loss": 0.1060481071472168,
+      "eval_precision": 0.9670443457655469,
+      "eval_recall": 0.9702903038900321,
+      "eval_runtime": 3.5348,
+      "eval_samples_per_second": 467.913,
+      "eval_steps_per_second": 29.421,
+      "step": 600
+    },
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.9751444401145355,
+      "eval_f1": 0.972691003391183,
+      "eval_loss": 0.09304744005203247,
+      "eval_precision": 0.9711605489055747,
+      "eval_recall": 0.9742262891850313,
+      "eval_runtime": 3.5404,
+      "eval_samples_per_second": 467.179,
+      "eval_steps_per_second": 29.375,
+      "step": 900
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.607541899441341e-06,
+      "loss": 0.0981,
+      "step": 1000
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.9768726385523797,
+      "eval_f1": 0.9757217127518386,
+      "eval_loss": 0.0842280164361,
+      "eval_precision": 0.9746421594035326,
+      "eval_recall": 0.9768036602665281,
+      "eval_runtime": 3.5912,
+      "eval_samples_per_second": 460.574,
+      "eval_steps_per_second": 28.96,
+      "step": 1200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.9092178770949727e-06,
+      "loss": 0.0752,
+      "step": 1500
+    },
+    {
+      "epoch": 1.68,
+      "eval_accuracy": 0.9773131597228105,
+      "eval_f1": 0.9761464958613322,
+      "eval_loss": 0.0810752809047699,
+      "eval_precision": 0.9756496746636861,
+      "eval_recall": 0.9766438233002338,
+      "eval_runtime": 3.5387,
+      "eval_samples_per_second": 467.408,
+      "eval_steps_per_second": 29.39,
+      "step": 1500
+    },
+    {
+      "epoch": 2.01,
+      "eval_accuracy": 0.9785669507463445,
+      "eval_f1": 0.9775089095864156,
+      "eval_loss": 0.07652546465396881,
+      "eval_precision": 0.9768165675751167,
+      "eval_recall": 0.978202233721604,
+      "eval_runtime": 3.5669,
+      "eval_samples_per_second": 463.705,
+      "eval_steps_per_second": 29.157,
+      "step": 1800
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 2.2108938547486037e-06,
+      "loss": 0.0665,
+      "step": 2000
+    },
+    {
+      "epoch": 2.35,
+      "eval_accuracy": 0.9788888700631978,
+      "eval_f1": 0.9777791081709423,
+      "eval_loss": 0.07642523944377899,
+      "eval_precision": 0.9766194937213474,
+      "eval_recall": 0.9789414796907154,
+      "eval_runtime": 3.5528,
+      "eval_samples_per_second": 465.546,
+      "eval_steps_per_second": 29.273,
+      "step": 2100
+    },
+    {
+      "epoch": 2.68,
+      "eval_accuracy": 0.9798715711356975,
+      "eval_f1": 0.9788792845307728,
+      "eval_loss": 0.07392332702875137,
+      "eval_precision": 0.97805924005186,
+      "eval_recall": 0.9797007052806138,
+      "eval_runtime": 6.3431,
+      "eval_samples_per_second": 260.756,
+      "eval_steps_per_second": 16.396,
+      "step": 2400
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.5125698324022347e-06,
+      "loss": 0.0572,
+      "step": 2500
+    },
+    {
+      "epoch": 3.02,
+      "eval_accuracy": 0.980379864793887,
+      "eval_f1": 0.9797258851832258,
+      "eval_loss": 0.07377304136753082,
+      "eval_precision": 0.9789929377967522,
+      "eval_recall": 0.9804599308705121,
+      "eval_runtime": 3.5438,
+      "eval_samples_per_second": 466.727,
+      "eval_steps_per_second": 29.347,
+      "step": 2700
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 8.142458100558661e-07,
+      "loss": 0.0517,
+      "step": 3000
+    },
+    {
+      "epoch": 3.35,
+      "eval_accuracy": 0.979939343623456,
+      "eval_f1": 0.9793008417457987,
+      "eval_loss": 0.07385215163230896,
+      "eval_precision": 0.9788414707173939,
+      "eval_recall": 0.9797606441429741,
+      "eval_runtime": 3.532,
+      "eval_samples_per_second": 468.288,
+      "eval_steps_per_second": 29.445,
+      "step": 3000
+    },
+    {
+      "epoch": 3.69,
+      "eval_accuracy": 0.9801257179647922,
+      "eval_f1": 0.9793164031304904,
+      "eval_loss": 0.07265603542327881,
+      "eval_precision": 0.9785935162094763,
+      "eval_recall": 0.9800403588339893,
+      "eval_runtime": 3.5347,
+      "eval_samples_per_second": 467.935,
+      "eval_steps_per_second": 29.423,
+      "step": 3300
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.1592178770949721e-07,
+      "loss": 0.0501,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "step": 3580,
+      "total_flos": 338555299892352.0,
+      "train_loss": 0.1316441932870023,
+      "train_runtime": 1079.4521,
+      "train_samples_per_second": 53.008,
+      "train_steps_per_second": 3.316
+    }
+  ],
+  "max_steps": 3580,
+  "num_train_epochs": 4,
+  "total_flos": 338555299892352.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e1e448a30bb2c08783bce7e807c24e97c01fef0a1ec658ac1055455adb62d6
+size 2863