adding model finetuned on POS

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9816844851832399,
+    "eval_f1": 0.980655593707578,
+    "eval_loss": 0.06724460422992706,
+    "eval_precision": 0.9798535894520575,
+    "eval_recall": 0.9814589119098519,
+    "eval_runtime": 8.3111,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 199.011,
+    "eval_steps_per_second": 6.257,
+    "train_loss": 0.12245277049286026,
+    "train_runtime": 1186.9763,
+    "train_samples": 14305,
+    "train_samples_per_second": 48.207,
+    "train_steps_per_second": 1.51
+}

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "CenIA/albert_xlarge_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": 2048,
+  "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": 8192,
+  "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": 32,
+  "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": 0.9816844851832399,
+    "eval_f1": 0.980655593707578,
+    "eval_loss": 0.06724460422992706,
+    "eval_precision": 0.9798535894520575,
+    "eval_recall": 0.9814589119098519,
+    "eval_runtime": 8.3111,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 199.011,
+    "eval_steps_per_second": 6.257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e2a041525cf09565fb00107fb7f45003a7ec9fa5dc9f60090279f1966b9c5d
+size 218787799

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_xlarge_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.12245277049286026,
+    "train_runtime": 1186.9763,
+    "train_samples": 14305,
+    "train_samples_per_second": 48.207,
+    "train_steps_per_second": 1.51
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": 0.06724460422992706,
+  "best_model_checkpoint": "/data/jcanete/all_results/pos/albeto_xlarge/epochs_4_bs_32_lr_5e-6/checkpoint-1600",
+  "epoch": 4.0,
+  "global_step": 1792,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.9701462191423391,
+      "eval_f1": 0.9659476055664102,
+      "eval_loss": 0.11576754599809647,
+      "eval_precision": 0.9638913757087436,
+      "eval_recall": 0.9680126271203373,
+      "eval_runtime": 8.2971,
+      "eval_samples_per_second": 199.347,
+      "eval_steps_per_second": 6.267,
+      "step": 200
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.9774148184544484,
+      "eval_f1": 0.9743559053233191,
+      "eval_loss": 0.08359552174806595,
+      "eval_precision": 0.9728518503764491,
+      "eval_recall": 0.9758646180895486,
+      "eval_runtime": 8.2688,
+      "eval_samples_per_second": 200.028,
+      "eval_steps_per_second": 6.289,
+      "step": 400
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.61328125e-06,
+      "loss": 0.3126,
+      "step": 500
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.9796174243066027,
+      "eval_f1": 0.9774613052497209,
+      "eval_loss": 0.07587467133998871,
+      "eval_precision": 0.9758069333545728,
+      "eval_recall": 0.9791212962777966,
+      "eval_runtime": 8.2627,
+      "eval_samples_per_second": 200.176,
+      "eval_steps_per_second": 6.293,
+      "step": 600
+    },
+    {
+      "epoch": 1.79,
+      "eval_accuracy": 0.981243964012809,
+      "eval_f1": 0.9795327764971211,
+      "eval_loss": 0.07019403576850891,
+      "eval_precision": 0.978487977989553,
+      "eval_recall": 0.9805798085952329,
+      "eval_runtime": 8.2592,
+      "eval_samples_per_second": 200.262,
+      "eval_steps_per_second": 6.296,
+      "step": 800
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 2.2181919642857142e-06,
+      "loss": 0.0602,
+      "step": 1000
+    },
+    {
+      "epoch": 2.23,
+      "eval_accuracy": 0.9813286796225072,
+      "eval_f1": 0.9797755051134948,
+      "eval_loss": 0.06836934387683868,
+      "eval_precision": 0.9785745605293579,
+      "eval_recall": 0.9809794010109688,
+      "eval_runtime": 8.2691,
+      "eval_samples_per_second": 200.021,
+      "eval_steps_per_second": 6.288,
+      "step": 1000
+    },
+    {
+      "epoch": 2.68,
+      "eval_accuracy": 0.981531997085783,
+      "eval_f1": 0.9803721997704935,
+      "eval_loss": 0.06962081789970398,
+      "eval_precision": 0.9792680009568615,
+      "eval_recall": 0.9814788915306387,
+      "eval_runtime": 8.2695,
+      "eval_samples_per_second": 200.012,
+      "eval_steps_per_second": 6.288,
+      "step": 1200
+    },
+    {
+      "epoch": 3.12,
+      "eval_accuracy": 0.9818369732806967,
+      "eval_f1": 0.9806183756162798,
+      "eval_loss": 0.06813845783472061,
+      "eval_precision": 0.9796797415598142,
+      "eval_recall": 0.981558810013786,
+      "eval_runtime": 8.2599,
+      "eval_samples_per_second": 200.245,
+      "eval_steps_per_second": 6.295,
+      "step": 1400
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 8.231026785714287e-07,
+      "loss": 0.0439,
+      "step": 1500
+    },
+    {
+      "epoch": 3.57,
+      "eval_accuracy": 0.9816844851832399,
+      "eval_f1": 0.980655593707578,
+      "eval_loss": 0.06724460422992706,
+      "eval_precision": 0.9798535894520575,
+      "eval_recall": 0.9814589119098519,
+      "eval_runtime": 8.2557,
+      "eval_samples_per_second": 200.345,
+      "eval_steps_per_second": 6.299,
+      "step": 1600
+    },
+    {
+      "epoch": 4.0,
+      "step": 1792,
+      "total_flos": 1487933302262400.0,
+      "train_loss": 0.12245277049286026,
+      "train_runtime": 1186.9763,
+      "train_samples_per_second": 48.207,
+      "train_steps_per_second": 1.51
+    }
+  ],
+  "max_steps": 1792,
+  "num_train_epochs": 4,
+  "total_flos": 1487933302262400.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7035699cd61759a140386f448891383124fe94096d0b9252d647a888f8ef3082
+size 2863