adding model fine-tuned on QA (TAR)

.gitattributes

@@ -26,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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": 59.90539262062441,
+    "eval_f1": 76.76435031260894,
+    "eval_samples": 10624,
+    "train_loss": 1.442597626205347,
+    "train_runtime": 4244.9763,
+    "train_samples": 87747,
+    "train_samples_per_second": 41.342,
+    "train_steps_per_second": 2.584
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "CenIA/albert_base_spanish",
+  "architectures": [
+    "AlbertForQuestionAnswering"
+  ],
+  "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,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "vocab_size": 31000
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60603bd31a8e072b247749097f5f596ba085440872d9e81bc4d921f79706af7
+size 44945824

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 59.90539262062441,
+    "eval_f1": 76.76435031260894,
+    "eval_samples": 10624
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f1de9a5db4c6cb63b5147fa43f39b820d5b32416d3ee3c6f9328cba245a1fe
+size 44904343

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_base_spanish", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.442597626205347,
+    "train_runtime": 4244.9763,
+    "train_samples": 87747,
+    "train_samples_per_second": 41.342,
+    "train_steps_per_second": 2.584
+}

trainer_state.json

@@ -0,0 +1,367 @@
+{
+  "best_metric": 76.76435031260894,
+  "best_model_checkpoint": "/data/jcanete/all_results/tar/albeto_base/epochs_2_bs_16_lr_5e-5/checkpoint-10800",
+  "epoch": 2.0,
+  "global_step": 10970,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "eval_exact_match": 47.086092715231786,
+      "eval_f1": 65.5171170026736,
+      "step": 300
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.774840474020055e-05,
+      "loss": 2.3269,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "eval_exact_match": 49.85808893093661,
+      "eval_f1": 68.52507945594036,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "eval_exact_match": 51.76915799432356,
+      "eval_f1": 69.56906516193933,
+      "step": 900
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.546946216955333e-05,
+      "loss": 1.8459,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22,
+      "eval_exact_match": 53.41532639545885,
+      "eval_f1": 71.48528779698195,
+      "step": 1200
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.319051959890611e-05,
+      "loss": 1.7369,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "eval_exact_match": 53.15042573320719,
+      "eval_f1": 71.44368531668232,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33,
+      "eval_exact_match": 54.12488174077578,
+      "eval_f1": 71.64759923228169,
+      "step": 1800
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.091157702825889e-05,
+      "loss": 1.6887,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "eval_exact_match": 55.45884578997162,
+      "eval_f1": 73.42042430837174,
+      "step": 2100
+    },
+    {
+      "epoch": 0.44,
+      "eval_exact_match": 54.56953642384106,
+      "eval_f1": 72.59697429491493,
+      "step": 2400
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.863263445761167e-05,
+      "loss": 1.6072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49,
+      "eval_exact_match": 56.50898770104068,
+      "eval_f1": 73.43029358496499,
+      "step": 2700
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.635369188696445e-05,
+      "loss": 1.6,
+      "step": 3000
+    },
+    {
+      "epoch": 0.55,
+      "eval_exact_match": 56.40491958372753,
+      "eval_f1": 74.21772073321748,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6,
+      "eval_exact_match": 56.87795648060549,
+      "eval_f1": 73.91971329572239,
+      "step": 3300
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.4074749316317225e-05,
+      "loss": 1.5774,
+      "step": 3500
+    },
+    {
+      "epoch": 0.66,
+      "eval_exact_match": 56.792809839167454,
+      "eval_f1": 74.43178170605586,
+      "step": 3600
+    },
+    {
+      "epoch": 0.71,
+      "eval_exact_match": 57.455061494796595,
+      "eval_f1": 74.7453977507605,
+      "step": 3900
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.1795806745670006e-05,
+      "loss": 1.5219,
+      "step": 4000
+    },
+    {
+      "epoch": 0.77,
+      "eval_exact_match": 57.379375591296125,
+      "eval_f1": 74.90229888644745,
+      "step": 4200
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.9521422060164085e-05,
+      "loss": 1.5288,
+      "step": 4500
+    },
+    {
+      "epoch": 0.82,
+      "eval_exact_match": 58.18353831598865,
+      "eval_f1": 75.22922707694818,
+      "step": 4500
+    },
+    {
+      "epoch": 0.88,
+      "eval_exact_match": 58.0321665089877,
+      "eval_f1": 75.07802882343144,
+      "step": 4800
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.7242479489516866e-05,
+      "loss": 1.498,
+      "step": 5000
+    },
+    {
+      "epoch": 0.93,
+      "eval_exact_match": 58.09839167455061,
+      "eval_f1": 74.95189255173474,
+      "step": 5100
+    },
+    {
+      "epoch": 0.98,
+      "eval_exact_match": 58.145695364238414,
+      "eval_f1": 75.38066842121376,
+      "step": 5400
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.4963536918869646e-05,
+      "loss": 1.4584,
+      "step": 5500
+    },
+    {
+      "epoch": 1.04,
+      "eval_exact_match": 58.59035004730369,
+      "eval_f1": 75.70324036867967,
+      "step": 5700
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.2684594348222427e-05,
+      "loss": 1.2389,
+      "step": 6000
+    },
+    {
+      "epoch": 1.09,
+      "eval_exact_match": 58.17407757805109,
+      "eval_f1": 75.51538938807475,
+      "step": 6000
+    },
+    {
+      "epoch": 1.15,
+      "eval_exact_match": 58.32544938505203,
+      "eval_f1": 75.61693026165182,
+      "step": 6300
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.0405651777575205e-05,
+      "loss": 1.2258,
+      "step": 6500
+    },
+    {
+      "epoch": 1.2,
+      "eval_exact_match": 58.533585619678334,
+      "eval_f1": 75.92726578627719,
+      "step": 6600
+    },
+    {
+      "epoch": 1.26,
+      "eval_exact_match": 59.08230842005676,
+      "eval_f1": 76.11468177341409,
+      "step": 6900
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8126709206927986e-05,
+      "loss": 1.2277,
+      "step": 7000
+    },
+    {
+      "epoch": 1.31,
+      "eval_exact_match": 59.0728476821192,
+      "eval_f1": 75.96454913273134,
+      "step": 7200
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.5856882406563355e-05,
+      "loss": 1.2335,
+      "step": 7500
+    },
+    {
+      "epoch": 1.37,
+      "eval_exact_match": 59.205298013245034,
+      "eval_f1": 75.86602680623224,
+      "step": 7500
+    },
+    {
+      "epoch": 1.42,
+      "eval_exact_match": 59.47019867549669,
+      "eval_f1": 76.36030755482952,
+      "step": 7800
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3577939835916137e-05,
+      "loss": 1.2338,
+      "step": 8000
+    },
+    {
+      "epoch": 1.48,
+      "eval_exact_match": 59.21475875118259,
+      "eval_f1": 76.38335355989443,
+      "step": 8100
+    },
+    {
+      "epoch": 1.53,
+      "eval_exact_match": 59.10122989593188,
+      "eval_f1": 76.29548834990918,
+      "step": 8400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.1298997265268915e-05,
+      "loss": 1.2125,
+      "step": 8500
+    },
+    {
+      "epoch": 1.59,
+      "eval_exact_match": 59.61210974456007,
+      "eval_f1": 76.39472052017639,
+      "step": 8700
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.020054694621696e-06,
+      "loss": 1.2036,
+      "step": 9000
+    },
+    {
+      "epoch": 1.64,
+      "eval_exact_match": 59.46073793755913,
+      "eval_f1": 76.45809431546856,
+      "step": 9000
+    },
+    {
+      "epoch": 1.7,
+      "eval_exact_match": 59.34720908230842,
+      "eval_f1": 76.33732861581315,
+      "step": 9300
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 6.741112123974476e-06,
+      "loss": 1.1853,
+      "step": 9500
+    },
+    {
+      "epoch": 1.75,
+      "eval_exact_match": 59.44181646168401,
+      "eval_f1": 76.52576561017717,
+      "step": 9600
+    },
+    {
+      "epoch": 1.8,
+      "eval_exact_match": 59.85808893093661,
+      "eval_f1": 76.59602193961624,
+      "step": 9900
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.4621695533272565e-06,
+      "loss": 1.1818,
+      "step": 10000
+    },
+    {
+      "epoch": 1.86,
+      "eval_exact_match": 59.69725638599811,
+      "eval_f1": 76.56922106601137,
+      "step": 10200
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.1832269826800365e-06,
+      "loss": 1.2171,
+      "step": 10500
+    },
+    {
+      "epoch": 1.91,
+      "eval_exact_match": 59.82970671712393,
+      "eval_f1": 76.66998900649348,
+      "step": 10500
+    },
+    {
+      "epoch": 1.97,
+      "eval_exact_match": 59.90539262062441,
+      "eval_f1": 76.76435031260894,
+      "step": 10800
+    },
+    {
+      "epoch": 2.0,
+      "step": 10970,
+      "total_flos": 2546174511427680.0,
+      "train_loss": 1.442597626205347,
+      "train_runtime": 4244.9763,
+      "train_samples_per_second": 41.342,
+      "train_steps_per_second": 2.584
+    }
+  ],
+  "max_steps": 10970,
+  "num_train_epochs": 2,
+  "total_flos": 2546174511427680.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088e1ccf10494e21c0ddf0ca8db5425d4d0ee5f6433ee2aa9ddaf0062359d256
+size 2991