best albert-xxlarge finetuned on ner

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9697488960653793,
+    "eval_f1": 0.8438369228323929,
+    "eval_loss": 0.12305136024951935,
+    "eval_precision": 0.8397658968680797,
+    "eval_recall": 0.8479476122025236,
+    "eval_runtime": 24.6046,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 77.871,
+    "eval_steps_per_second": 19.468,
+    "train_loss": 0.10445189647949658,
+    "train_runtime": 732.081,
+    "train_samples": 8324,
+    "train_samples_per_second": 22.741,
+    "train_steps_per_second": 1.421
+}

config.json

@@ -0,0 +1,57 @@
+{
+  "_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": "ner",
+  "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"
+  },
+  "initializer_range": 0.01,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "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-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": "4.11.3",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9697488960653793,
+    "eval_f1": 0.8438369228323929,
+    "eval_loss": 0.12305136024951935,
+    "eval_precision": 0.8397658968680797,
+    "eval_recall": 0.8479476122025236,
+    "eval_runtime": 24.6046,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 77.871,
+    "eval_steps_per_second": 19.468
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b3b54357a2b22edd9229096506e8439134c6543ea67e46586705b2aac671bf
+size 823930775

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": 2.0,
+    "train_loss": 0.10445189647949658,
+    "train_runtime": 732.081,
+    "train_samples": 8324,
+    "train_samples_per_second": 22.741,
+    "train_steps_per_second": 1.421
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": 0.12305136024951935,
+  "best_model_checkpoint": "/home/sdonoso/data/all_results/ner-c/albert-xxlarge/epochs_2_bs_4_lr_2e-5/checkpoint-1000",
+  "epoch": 1.9995194617972127,
+  "global_step": 1040,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0442307692307694e-05,
+      "loss": 0.158,
+      "step": 500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.26923076923077e-07,
+      "loss": 0.0558,
+      "step": 1000
+    },
+    {
+      "epoch": 1.92,
+      "eval_accuracy": 0.9697488960653793,
+      "eval_f1": 0.8438369228323929,
+      "eval_loss": 0.12305136024951935,
+      "eval_precision": 0.8397658968680797,
+      "eval_recall": 0.8479476122025236,
+      "eval_runtime": 26.2148,
+      "eval_samples_per_second": 73.088,
+      "eval_steps_per_second": 18.272,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "step": 1040,
+      "total_flos": 1325433589814784.0,
+      "train_loss": 0.10445189647949658,
+      "train_runtime": 732.081,
+      "train_samples_per_second": 22.741,
+      "train_steps_per_second": 1.421
+    }
+  ],
+  "max_steps": 1040,
+  "num_train_epochs": 2,
+  "total_flos": 1325433589814784.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0bb3fe5777216ba6d26521f57652b902803200ef52bf52a333ebea8fc1c4a6
+size 2863