adding model finetuned on tar

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 59.6310312204352,
+    "eval_f1": 76.36038789574842,
+    "eval_samples": 10624,
+    "train_loss": 1.452151380763232,
+    "train_runtime": 2009.9163,
+    "train_samples": 87747,
+    "train_samples_per_second": 87.314,
+    "train_steps_per_second": 5.458
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "dccuchile/albert-base-10-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": 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 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 59.6310312204352,
+    "eval_f1": 76.36038789574842,
+    "eval_samples": 10624
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc072037d60f5feaa123a4e78773744cc1becb43290b249d6b4c1a39f3e62b20
+size 44903231

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 +1,23 @@
+{
+  "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": 2.0,
+    "train_loss": 1.452151380763232,
+    "train_runtime": 2009.9163,
+    "train_samples": 87747,
+    "train_samples_per_second": 87.314,
+    "train_steps_per_second": 5.458
+}

trainer_state.json

@@ -0,0 +1,367 @@
+{
+  "best_metric": 76.36038789574842,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/tar/albeto_base_10/epochs_2_bs_16_lr_5e-5/checkpoint-10200",
+  "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": 45.53453169347209,
+      "eval_f1": 64.38889275299238,
+      "step": 300
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.774840474020055e-05,
+      "loss": 2.3938,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "eval_exact_match": 49.14853358561968,
+      "eval_f1": 67.53518688183068,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "eval_exact_match": 51.26773888363292,
+      "eval_f1": 69.15241192316618,
+      "step": 900
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.546946216955333e-05,
+      "loss": 1.8676,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22,
+      "eval_exact_match": 52.677388836329236,
+      "eval_f1": 71.264646480928,
+      "step": 1200
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.319051959890611e-05,
+      "loss": 1.7557,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "eval_exact_match": 52.8003784295175,
+      "eval_f1": 70.69843839338733,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33,
+      "eval_exact_match": 53.841059602649004,
+      "eval_f1": 71.55219520099376,
+      "step": 1800
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.091157702825889e-05,
+      "loss": 1.7093,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "eval_exact_match": 54.08703878902554,
+      "eval_f1": 72.75312871370792,
+      "step": 2100
+    },
+    {
+      "epoch": 0.44,
+      "eval_exact_match": 54.15326395458846,
+      "eval_f1": 72.25373492579445,
+      "step": 2400
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.863263445761167e-05,
+      "loss": 1.6266,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49,
+      "eval_exact_match": 55.81835383159886,
+      "eval_f1": 73.13623090017391,
+      "step": 2700
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.635369188696445e-05,
+      "loss": 1.6179,
+      "step": 3000
+    },
+    {
+      "epoch": 0.55,
+      "eval_exact_match": 56.017029328287606,
+      "eval_f1": 73.68563507466432,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6,
+      "eval_exact_match": 57.03878902554399,
+      "eval_f1": 73.81599366386958,
+      "step": 3300
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.4074749316317225e-05,
+      "loss": 1.5863,
+      "step": 3500
+    },
+    {
+      "epoch": 0.66,
+      "eval_exact_match": 56.9441816461684,
+      "eval_f1": 74.03932269687274,
+      "step": 3600
+    },
+    {
+      "epoch": 0.71,
+      "eval_exact_match": 57.11447492904446,
+      "eval_f1": 74.25288243781013,
+      "step": 3900
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.1795806745670006e-05,
+      "loss": 1.5291,
+      "step": 4000
+    },
+    {
+      "epoch": 0.77,
+      "eval_exact_match": 57.63481551561022,
+      "eval_f1": 74.89927170312892,
+      "step": 4200
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.951686417502279e-05,
+      "loss": 1.5386,
+      "step": 4500
+    },
+    {
+      "epoch": 0.82,
+      "eval_exact_match": 57.95648060548723,
+      "eval_f1": 74.61884384474561,
+      "step": 4500
+    },
+    {
+      "epoch": 0.88,
+      "eval_exact_match": 58.02270577105014,
+      "eval_f1": 75.32600315809357,
+      "step": 4800
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.723792160437557e-05,
+      "loss": 1.5132,
+      "step": 5000
+    },
+    {
+      "epoch": 0.93,
+      "eval_exact_match": 58.306527909176914,
+      "eval_f1": 74.89942757720935,
+      "step": 5100
+    },
+    {
+      "epoch": 0.98,
+      "eval_exact_match": 58.64711447492905,
+      "eval_f1": 75.59723967213186,
+      "step": 5400
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.4958979033728353e-05,
+      "loss": 1.4682,
+      "step": 5500
+    },
+    {
+      "epoch": 1.04,
+      "eval_exact_match": 59.15799432355724,
+      "eval_f1": 75.83737312760167,
+      "step": 5700
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.268003646308113e-05,
+      "loss": 1.2319,
+      "step": 6000
+    },
+    {
+      "epoch": 1.09,
+      "eval_exact_match": 58.609271523178805,
+      "eval_f1": 75.81477740927686,
+      "step": 6000
+    },
+    {
+      "epoch": 1.15,
+      "eval_exact_match": 58.59035004730369,
+      "eval_f1": 75.43205542917899,
+      "step": 6300
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.040109389243391e-05,
+      "loss": 1.2259,
+      "step": 6500
+    },
+    {
+      "epoch": 1.2,
+      "eval_exact_match": 58.77010406811731,
+      "eval_f1": 75.82376993425314,
+      "step": 6600
+    },
+    {
+      "epoch": 1.26,
+      "eval_exact_match": 58.24976348155156,
+      "eval_f1": 75.0320889415698,
+      "step": 6900
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8122151321786692e-05,
+      "loss": 1.2123,
+      "step": 7000
+    },
+    {
+      "epoch": 1.31,
+      "eval_exact_match": 58.98770104068117,
+      "eval_f1": 76.02527498333018,
+      "step": 7200
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.5847766636280767e-05,
+      "loss": 1.1885,
+      "step": 7500
+    },
+    {
+      "epoch": 1.37,
+      "eval_exact_match": 58.9120151371807,
+      "eval_f1": 76.0439212810425,
+      "step": 7500
+    },
+    {
+      "epoch": 1.42,
+      "eval_exact_match": 58.826868495742666,
+      "eval_f1": 75.94488358894192,
+      "step": 7800
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3568824065633548e-05,
+      "loss": 1.2468,
+      "step": 8000
+    },
+    {
+      "epoch": 1.48,
+      "eval_exact_match": 59.3282876064333,
+      "eval_f1": 76.00751273155576,
+      "step": 8100
+    },
+    {
+      "epoch": 1.53,
+      "eval_exact_match": 58.99716177861873,
+      "eval_f1": 75.85711081597596,
+      "step": 8400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.1289881494986327e-05,
+      "loss": 1.2093,
+      "step": 8500
+    },
+    {
+      "epoch": 1.59,
+      "eval_exact_match": 59.04446546830653,
+      "eval_f1": 75.83015637646359,
+      "step": 8700
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.010938924339108e-06,
+      "loss": 1.2199,
+      "step": 9000
+    },
+    {
+      "epoch": 1.64,
+      "eval_exact_match": 59.10122989593188,
+      "eval_f1": 76.0261318966032,
+      "step": 9000
+    },
+    {
+      "epoch": 1.7,
+      "eval_exact_match": 59.0728476821192,
+      "eval_f1": 76.13920824424939,
+      "step": 9300
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 6.731996353691887e-06,
+      "loss": 1.2102,
+      "step": 9500
+    },
+    {
+      "epoch": 1.75,
+      "eval_exact_match": 59.0728476821192,
+      "eval_f1": 76.09156663606447,
+      "step": 9600
+    },
+    {
+      "epoch": 1.8,
+      "eval_exact_match": 59.47965941343425,
+      "eval_f1": 76.2619678916128,
+      "step": 9900
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.453053783044668e-06,
+      "loss": 1.1986,
+      "step": 10000
+    },
+    {
+      "epoch": 1.86,
+      "eval_exact_match": 59.6310312204352,
+      "eval_f1": 76.36038789574842,
+      "step": 10200
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.174111212397448e-06,
+      "loss": 1.2024,
+      "step": 10500
+    },
+    {
+      "epoch": 1.91,
+      "eval_exact_match": 59.39451277199622,
+      "eval_f1": 76.24512822926708,
+      "step": 10500
+    },
+    {
+      "epoch": 1.97,
+      "eval_exact_match": 59.593188268684955,
+      "eval_f1": 76.29176107833557,
+      "step": 10800
+    },
+    {
+      "epoch": 2.0,
+      "step": 10970,
+      "total_flos": 2544773915225664.0,
+      "train_loss": 1.452151380763232,
+      "train_runtime": 2009.9163,
+      "train_samples_per_second": 87.314,
+      "train_steps_per_second": 5.458
+    }
+  ],
+  "max_steps": 10970,
+  "num_train_epochs": 2,
+  "total_flos": 2544773915225664.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1aca32c97fd106b2614462fee0df8a8f3f291faa44dc14d52196e29c437c0d
+size 3515