adding model finetuned on tar

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 60.416272469252604,
+    "eval_f1": 77.32269615784104,
+    "eval_samples": 10617,
+    "train_loss": 1.2413271612987178,
+    "train_runtime": 3098.796,
+    "train_samples": 87748,
+    "train_samples_per_second": 56.634,
+    "train_steps_per_second": 1.77
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-large-bne",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc4101752ec9b45192e86ff64963a1b09eed3c6daf8af8ed13c2a9c1207066d
+size 45011119

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 60.416272469252604,
+    "eval_f1": 77.32269615784104,
+    "eval_samples": 10617
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3268164cf22caf99b3c53333dce4e0b2c004bf1d19923257025c5d62e2adbc7f
+size 1417373041

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_len": 512,
+  "name_or_path": "PlanTL-GOB-ES/roberta-large-bne",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.2413271612987178,
+    "train_runtime": 3098.796,
+    "train_samples": 87748,
+    "train_samples_per_second": 56.634,
+    "train_steps_per_second": 1.77
+}

trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 77.32269615784104,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/tar/roberta_large_bne/epochs_2_bs_32_lr_2e-5/checkpoint-4500",
+  "epoch": 2.0,
+  "global_step": 5486,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "eval_exact_match": 52.72469252601703,
+      "eval_f1": 70.31979377504159,
+      "step": 300
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8177178271965002e-05,
+      "loss": 2.0124,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "eval_exact_match": 55.37369914853358,
+      "eval_f1": 72.79425345069818,
+      "step": 600
+    },
+    {
+      "epoch": 0.33,
+      "eval_exact_match": 57.142857142857146,
+      "eval_f1": 74.00444934296571,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6354356543930007e-05,
+      "loss": 1.6158,
+      "step": 1000
+    },
+    {
+      "epoch": 0.44,
+      "eval_exact_match": 57.899716177861876,
+      "eval_f1": 75.07716154126113,
+      "step": 1200
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.4531534815895008e-05,
+      "loss": 1.5421,
+      "step": 1500
+    },
+    {
+      "epoch": 0.55,
+      "eval_exact_match": 59.08230842005676,
+      "eval_f1": 75.72655876274406,
+      "step": 1500
+    },
+    {
+      "epoch": 0.66,
+      "eval_exact_match": 58.77010406811731,
+      "eval_f1": 75.5986676698771,
+      "step": 1800
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.2712358731316079e-05,
+      "loss": 1.4971,
+      "step": 2000
+    },
+    {
+      "epoch": 0.77,
+      "eval_exact_match": 59.40397350993378,
+      "eval_f1": 76.56550651885689,
+      "step": 2100
+    },
+    {
+      "epoch": 0.87,
+      "eval_exact_match": 60.33112582781457,
+      "eval_f1": 77.04475615318619,
+      "step": 2400
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0889537003281081e-05,
+      "loss": 1.4532,
+      "step": 2500
+    },
+    {
+      "epoch": 0.98,
+      "eval_exact_match": 60.179754020813625,
+      "eval_f1": 76.98820150102628,
+      "step": 2700
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.066715275246082e-06,
+      "loss": 1.1553,
+      "step": 3000
+    },
+    {
+      "epoch": 1.09,
+      "eval_exact_match": 59.735099337748345,
+      "eval_f1": 76.60782983695076,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2,
+      "eval_exact_match": 59.7918637653737,
+      "eval_f1": 76.76732218063003,
+      "step": 3300
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 7.243893547211084e-06,
+      "loss": 0.9124,
+      "step": 3500
+    },
+    {
+      "epoch": 1.31,
+      "eval_exact_match": 59.83916745506149,
+      "eval_f1": 76.96753684496848,
+      "step": 3600
+    },
+    {
+      "epoch": 1.42,
+      "eval_exact_match": 59.99053926206244,
+      "eval_f1": 76.84857447005851,
+      "step": 3900
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.421071819176085e-06,
+      "loss": 0.8835,
+      "step": 4000
+    },
+    {
+      "epoch": 1.53,
+      "eval_exact_match": 59.422894985808895,
+      "eval_f1": 76.94657837246879,
+      "step": 4200
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 3.6018957345971567e-06,
+      "loss": 0.8727,
+      "step": 4500
+    },
+    {
+      "epoch": 1.64,
+      "eval_exact_match": 60.416272469252604,
+      "eval_f1": 77.32269615784104,
+      "step": 4500
+    },
+    {
+      "epoch": 1.75,
+      "eval_exact_match": 60.2081362346263,
+      "eval_f1": 77.1919063305815,
+      "step": 4800
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.7827196500182284e-06,
+      "loss": 0.8503,
+      "step": 5000
+    },
+    {
+      "epoch": 1.86,
+      "eval_exact_match": 60.06622516556291,
+      "eval_f1": 77.17743863949298,
+      "step": 5100
+    },
+    {
+      "epoch": 1.97,
+      "eval_exact_match": 60.31220435193945,
+      "eval_f1": 77.30000861688039,
+      "step": 5400
+    },
+    {
+      "epoch": 2.0,
+      "step": 5486,
+      "total_flos": 1.1863529489772403e+17,
+      "train_loss": 1.2413271612987178,
+      "train_runtime": 3098.796,
+      "train_samples_per_second": 56.634,
+      "train_steps_per_second": 1.77
+    }
+  ],
+  "max_steps": 5486,
+  "num_train_epochs": 2,
+  "total_flos": 1.1863529489772403e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f0835a502bb645911344d72f18ac555d327af66e05fa7114599373980481be
+size 3439