adding model finetuned on POS

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9914882064549099,
+    "eval_f1": 0.9899645514004692,
+    "eval_loss": 0.032893065363168716,
+    "eval_precision": 0.9895396654289935,
+    "eval_recall": 0.9903898024015504,
+    "eval_runtime": 2.9491,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 560.854,
+    "eval_steps_per_second": 35.265,
+    "train_loss": 0.05748698165296842,
+    "train_runtime": 136.7323,
+    "train_samples": 14305,
+    "train_samples_per_second": 209.241,
+    "train_steps_per_second": 13.091
+}

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "pos",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "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",
+    "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,
+  "intermediate_size": 3072,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9914882064549099,
+    "eval_f1": 0.9899645514004692,
+    "eval_loss": 0.032893065363168716,
+    "eval_precision": 0.9895396654289935,
+    "eval_recall": 0.9903898024015504,
+    "eval_runtime": 2.9491,
+    "eval_samples": 1654,
+    "eval_samples_per_second": 560.854,
+    "eval_steps_per_second": 35.265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e837180ae7db3ee6218e8df22a8f2497706f03bd38fd55bd88ef9d2680817c92
+size 496351025

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "PlanTL-GOB-ES/roberta-base-bne", "do_lower_case": false, "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.05748698165296842,
+    "train_runtime": 136.7323,
+    "train_samples": 14305,
+    "train_samples_per_second": 209.241,
+    "train_steps_per_second": 13.091
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": 0.032893065363168716,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/pos/roberta_base_bne/epochs_2_bs_16_lr_5e-5/checkpoint-1600",
+  "epoch": 2.0,
+  "global_step": 1790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.984541433111356,
+      "eval_f1": 0.9812364013813204,
+      "eval_loss": 0.06434043496847153,
+      "eval_precision": 0.9803362383582953,
+      "eval_recall": 0.982138219016603,
+      "eval_runtime": 2.9618,
+      "eval_samples_per_second": 558.44,
+      "eval_steps_per_second": 35.114,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.9877832606716811,
+      "eval_f1": 0.9851088887558137,
+      "eval_loss": 0.04959944263100624,
+      "eval_precision": 0.9842051732046347,
+      "eval_recall": 0.9860142654492418,
+      "eval_runtime": 2.9534,
+      "eval_samples_per_second": 560.023,
+      "eval_steps_per_second": 35.213,
+      "step": 400
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.603351955307263e-05,
+      "loss": 0.1416,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9888212842747409,
+      "eval_f1": 0.9869598210719706,
+      "eval_loss": 0.0426110178232193,
+      "eval_precision": 0.9864673359813178,
+      "eval_recall": 0.9874527981458912,
+      "eval_runtime": 2.954,
+      "eval_samples_per_second": 559.912,
+      "eval_steps_per_second": 35.206,
+      "step": 600
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.9898912470655872,
+      "eval_f1": 0.9885165361878895,
+      "eval_loss": 0.03891567513346672,
+      "eval_precision": 0.9881021300381291,
+      "eval_recall": 0.9889312900841142,
+      "eval_runtime": 2.9458,
+      "eval_samples_per_second": 561.485,
+      "eval_steps_per_second": 35.305,
+      "step": 800
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.206703910614525e-05,
+      "loss": 0.0348,
+      "step": 1000
+    },
+    {
+      "epoch": 1.12,
+      "eval_accuracy": 0.9904182436640636,
+      "eval_f1": 0.9885959656480927,
+      "eval_loss": 0.03714817017316818,
+      "eval_precision": 0.9882209666793108,
+      "eval_recall": 0.9889712493256878,
+      "eval_runtime": 2.9497,
+      "eval_samples_per_second": 560.735,
+      "eval_steps_per_second": 35.258,
+      "step": 1000
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.990514061227423,
+      "eval_f1": 0.9887465425824039,
+      "eval_loss": 0.03583846241235733,
+      "eval_precision": 0.9883024592781858,
+      "eval_recall": 0.9891910251543425,
+      "eval_runtime": 2.9981,
+      "eval_samples_per_second": 551.674,
+      "eval_steps_per_second": 34.688,
+      "step": 1200
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy": 0.9909133010747536,
+      "eval_f1": 0.9891582142001439,
+      "eval_loss": 0.03380614146590233,
+      "eval_precision": 0.9885068938683481,
+      "eval_recall": 0.9898103933987333,
+      "eval_runtime": 2.9525,
+      "eval_samples_per_second": 560.202,
+      "eval_steps_per_second": 35.224,
+      "step": 1400
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.100558659217877e-06,
+      "loss": 0.0202,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "eval_accuracy": 0.9914882064549099,
+      "eval_f1": 0.9899645514004692,
+      "eval_loss": 0.032893065363168716,
+      "eval_precision": 0.9895396654289935,
+      "eval_recall": 0.9903898024015504,
+      "eval_runtime": 2.9564,
+      "eval_samples_per_second": 559.471,
+      "eval_steps_per_second": 35.178,
+      "step": 1600
+    },
+    {
+      "epoch": 2.0,
+      "step": 1790,
+      "total_flos": 1190583063933120.0,
+      "train_loss": 0.05748698165296842,
+      "train_runtime": 136.7323,
+      "train_samples_per_second": 209.241,
+      "train_steps_per_second": 13.091
+    }
+  ],
+  "max_steps": 1790,
+  "num_train_epochs": 2,
+  "total_flos": 1190583063933120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72effdaeb9fec41d2df4800c55e5380d0f7326708624d83835b327d437460b4a
+size 2991