adding model finetuned on ner

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.962762802346273,
+    "eval_f1": 0.8076046822216985,
+    "eval_loss": 0.12875927984714508,
+    "eval_precision": 0.7946815089672232,
+    "eval_recall": 0.8209551189905766,
+    "eval_runtime": 1.8021,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 1063.206,
+    "eval_steps_per_second": 33.295,
+    "train_loss": 0.13201307291272044,
+    "train_runtime": 54.4964,
+    "train_samples": 8324,
+    "train_samples_per_second": 610.976,
+    "train_steps_per_second": 19.157
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "dccuchile/albert-base-10-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": 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,
+  "inner_group_num": 1,
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 10,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.962762802346273,
+    "eval_f1": 0.8076046822216985,
+    "eval_loss": 0.12875927984714508,
+    "eval_precision": 0.7946815089672232,
+    "eval_recall": 0.8209551189905766,
+    "eval_runtime": 1.8021,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 1063.206,
+    "eval_steps_per_second": 33.295
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f11f759e49099b627deb052ee91fcc9e089b5d549996206906f7dac8f739236
+size 44924735

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "dccuchile/albert-base-10-spanish",
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.13201307291272044,
+    "train_runtime": 54.4964,
+    "train_samples": 8324,
+    "train_samples_per_second": 610.976,
+    "train_steps_per_second": 19.157
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.12875927984714508,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/ner/albeto_base_10/epochs_4_bs_32_lr_5e-5/checkpoint-700",
+  "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": 0.9292493244579186,
+      "eval_f1": 0.6192774836499534,
+      "eval_loss": 0.2619832754135132,
+      "eval_precision": 0.6041318547774571,
+      "eval_recall": 0.6352020444018528,
+      "eval_runtime": 1.8554,
+      "eval_samples_per_second": 1032.641,
+      "eval_steps_per_second": 32.337,
+      "step": 100
+    },
+    {
+      "epoch": 0.77,
+      "eval_accuracy": 0.9522177552230936,
+      "eval_f1": 0.7341891045710708,
+      "eval_loss": 0.1654893010854721,
+      "eval_precision": 0.7198772064466615,
+      "eval_recall": 0.7490816163552149,
+      "eval_runtime": 1.7972,
+      "eval_samples_per_second": 1066.105,
+      "eval_steps_per_second": 33.385,
+      "step": 200
+    },
+    {
+      "epoch": 1.15,
+      "eval_accuracy": 0.9579516245963224,
+      "eval_f1": 0.7919559492458702,
+      "eval_loss": 0.149013951420784,
+      "eval_precision": 0.7913875598086124,
+      "eval_recall": 0.7925251557259224,
+      "eval_runtime": 1.8699,
+      "eval_samples_per_second": 1024.659,
+      "eval_steps_per_second": 32.087,
+      "step": 300
+    },
+    {
+      "epoch": 1.53,
+      "eval_accuracy": 0.9607032228300271,
+      "eval_f1": 0.7946535126103907,
+      "eval_loss": 0.13737879693508148,
+      "eval_precision": 0.7916930881420419,
+      "eval_recall": 0.7976361603577703,
+      "eval_runtime": 1.8043,
+      "eval_samples_per_second": 1061.881,
+      "eval_steps_per_second": 33.253,
+      "step": 400
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.6149425287356323e-05,
+      "loss": 0.2123,
+      "step": 500
+    },
+    {
+      "epoch": 1.92,
+      "eval_accuracy": 0.9636525406972912,
+      "eval_f1": 0.8209348781462246,
+      "eval_loss": 0.12951940298080444,
+      "eval_precision": 0.8213943076431084,
+      "eval_recall": 0.8204759623063408,
+      "eval_runtime": 1.7875,
+      "eval_samples_per_second": 1071.873,
+      "eval_steps_per_second": 33.566,
+      "step": 500
+    },
+    {
+      "epoch": 2.3,
+      "eval_accuracy": 0.9627463257101431,
+      "eval_f1": 0.8149384187524832,
+      "eval_loss": 0.13606947660446167,
+      "eval_precision": 0.8108791903858318,
+      "eval_recall": 0.8190384922536336,
+      "eval_runtime": 1.798,
+      "eval_samples_per_second": 1065.622,
+      "eval_steps_per_second": 33.37,
+      "step": 600
+    },
+    {
+      "epoch": 2.68,
+      "eval_accuracy": 0.962762802346273,
+      "eval_f1": 0.8076046822216985,
+      "eval_loss": 0.12875927984714508,
+      "eval_precision": 0.7946815089672232,
+      "eval_recall": 0.8209551189905766,
+      "eval_runtime": 1.8023,
+      "eval_samples_per_second": 1063.059,
+      "eval_steps_per_second": 33.29,
+      "step": 700
+    },
+    {
+      "epoch": 3.07,
+      "eval_accuracy": 0.9635866341527713,
+      "eval_f1": 0.8158271094867312,
+      "eval_loss": 0.1313953548669815,
+      "eval_precision": 0.811699604743083,
+      "eval_recall": 0.8199968056221051,
+      "eval_runtime": 1.7921,
+      "eval_samples_per_second": 1069.118,
+      "eval_steps_per_second": 33.48,
+      "step": 800
+    },
+    {
+      "epoch": 3.45,
+      "eval_accuracy": 0.9627957556185329,
+      "eval_f1": 0.8106307021023402,
+      "eval_loss": 0.13798536360263824,
+      "eval_precision": 0.805327868852459,
+      "eval_recall": 0.8160038332534739,
+      "eval_runtime": 1.8024,
+      "eval_samples_per_second": 1063.055,
+      "eval_steps_per_second": 33.29,
+      "step": 900
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 2.2030651340996167e-06,
+      "loss": 0.0591,
+      "step": 1000
+    },
+    {
+      "epoch": 3.83,
+      "eval_accuracy": 0.9642292229618401,
+      "eval_f1": 0.818637194879542,
+      "eval_loss": 0.13375717401504517,
+      "eval_precision": 0.8150728309056364,
+      "eval_recall": 0.8222328701485385,
+      "eval_runtime": 1.8609,
+      "eval_samples_per_second": 1029.628,
+      "eval_steps_per_second": 32.243,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "step": 1044,
+      "total_flos": 139056718739136.0,
+      "train_loss": 0.13201307291272044,
+      "train_runtime": 54.4964,
+      "train_samples_per_second": 610.976,
+      "train_steps_per_second": 19.157
+    }
+  ],
+  "max_steps": 1044,
+  "num_train_epochs": 4,
+  "total_flos": 139056718739136.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb04e2fe77b78e24e2aa9383d8588e3357db765af6e1da095823a249c11ae15
+size 3515