adding model finetuned on tar

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 57.28476821192053,
+    "eval_f1": 74.36995381137226,
+    "eval_samples": 10624,
+    "train_loss": 1.524520064486953,
+    "train_runtime": 1743.0774,
+    "train_samples": 87747,
+    "train_samples_per_second": 100.681,
+    "train_steps_per_second": 6.293
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "dccuchile/albert-base-6-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": 6,
+  "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": 57.28476821192053,
+    "eval_f1": 74.36995381137226,
+    "eval_samples": 10624
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d07e086501fa1852ac3f3d3c80ed17d8c5ab457edd9854ffdc91e153e187ecf
+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-6-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": 1.524520064486953,
+    "train_runtime": 1743.0774,
+    "train_samples": 87747,
+    "train_samples_per_second": 100.681,
+    "train_steps_per_second": 6.293
+}

trainer_state.json

@@ -0,0 +1,367 @@
+{
+  "best_metric": 74.36995381137226,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/tar/albeto_base_6/epochs_2_bs_16_lr_5e-5/checkpoint-8700",
+  "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": 40.719016083254495,
+      "eval_f1": 58.77945049839472,
+      "step": 300
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.773473108477667e-05,
+      "loss": 2.5693,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "eval_exact_match": 45.44938505203406,
+      "eval_f1": 63.936960472857905,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "eval_exact_match": 48.42005676442763,
+      "eval_f1": 66.7942849285666,
+      "step": 900
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.545578851412944e-05,
+      "loss": 1.9654,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22,
+      "eval_exact_match": 49.725638599810786,
+      "eval_f1": 68.05815355034528,
+      "step": 1200
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.3176845943482223e-05,
+      "loss": 1.8622,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "eval_exact_match": 50.37842951750237,
+      "eval_f1": 68.12485071659977,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33,
+      "eval_exact_match": 51.59886471144749,
+      "eval_f1": 69.3844758904365,
+      "step": 1800
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.0897903372835004e-05,
+      "loss": 1.8064,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "eval_exact_match": 52.92336802270577,
+      "eval_f1": 71.05206739179368,
+      "step": 2100
+    },
+    {
+      "epoch": 0.44,
+      "eval_exact_match": 52.535477767265846,
+      "eval_f1": 70.11029061313148,
+      "step": 2400
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.8618960802187785e-05,
+      "loss": 1.7133,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49,
+      "eval_exact_match": 52.904446546830656,
+      "eval_f1": 70.98616483675112,
+      "step": 2700
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.6340018231540566e-05,
+      "loss": 1.7045,
+      "step": 3000
+    },
+    {
+      "epoch": 0.55,
+      "eval_exact_match": 54.276253547776726,
+      "eval_f1": 71.66909074175824,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6,
+      "eval_exact_match": 54.46546830652791,
+      "eval_f1": 71.54479654097987,
+      "step": 3300
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.406107566089335e-05,
+      "loss": 1.6732,
+      "step": 3500
+    },
+    {
+      "epoch": 0.66,
+      "eval_exact_match": 55.0236518448439,
+      "eval_f1": 72.43165471889594,
+      "step": 3600
+    },
+    {
+      "epoch": 0.71,
+      "eval_exact_match": 55.21286660359508,
+      "eval_f1": 72.64020525017258,
+      "step": 3900
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.178213309024613e-05,
+      "loss": 1.6218,
+      "step": 4000
+    },
+    {
+      "epoch": 0.77,
+      "eval_exact_match": 55.581835383159884,
+      "eval_f1": 73.12194401332194,
+      "step": 4200
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.9503190519598906e-05,
+      "loss": 1.6245,
+      "step": 4500
+    },
+    {
+      "epoch": 0.82,
+      "eval_exact_match": 55.65752128666036,
+      "eval_f1": 72.86127958084641,
+      "step": 4500
+    },
+    {
+      "epoch": 0.88,
+      "eval_exact_match": 55.96026490066225,
+      "eval_f1": 73.4084850665819,
+      "step": 4800
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.7224247948951686e-05,
+      "loss": 1.6021,
+      "step": 5000
+    },
+    {
+      "epoch": 0.93,
+      "eval_exact_match": 56.40491958372753,
+      "eval_f1": 73.57999833438744,
+      "step": 5100
+    },
+    {
+      "epoch": 0.98,
+      "eval_exact_match": 56.34815515610217,
+      "eval_f1": 73.92632868373076,
+      "step": 5400
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.4949863263445765e-05,
+      "loss": 1.5458,
+      "step": 5500
+    },
+    {
+      "epoch": 1.04,
+      "eval_exact_match": 56.7360454115421,
+      "eval_f1": 73.96946840195473,
+      "step": 5700
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.2670920692798542e-05,
+      "loss": 1.2682,
+      "step": 6000
+    },
+    {
+      "epoch": 1.09,
+      "eval_exact_match": 56.71712393566698,
+      "eval_f1": 73.83807242592808,
+      "step": 6000
+    },
+    {
+      "epoch": 1.15,
+      "eval_exact_match": 56.61305581835383,
+      "eval_f1": 73.47868870604212,
+      "step": 6300
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.0391978122151323e-05,
+      "loss": 1.2702,
+      "step": 6500
+    },
+    {
+      "epoch": 1.2,
+      "eval_exact_match": 56.08325449385052,
+      "eval_f1": 73.87945111610915,
+      "step": 6600
+    },
+    {
+      "epoch": 1.26,
+      "eval_exact_match": 56.395458845789975,
+      "eval_f1": 73.26116080395376,
+      "step": 6900
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8113035551504104e-05,
+      "loss": 1.2553,
+      "step": 7000
+    },
+    {
+      "epoch": 1.31,
+      "eval_exact_match": 56.50898770104068,
+      "eval_f1": 73.92339178593369,
+      "step": 7200
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.583409298085688e-05,
+      "loss": 1.2378,
+      "step": 7500
+    },
+    {
+      "epoch": 1.37,
+      "eval_exact_match": 56.471144749290445,
+      "eval_f1": 74.01594585064186,
+      "step": 7500
+    },
+    {
+      "epoch": 1.42,
+      "eval_exact_match": 56.61305581835383,
+      "eval_f1": 74.11650132906428,
+      "step": 7800
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3555150410209664e-05,
+      "loss": 1.3004,
+      "step": 8000
+    },
+    {
+      "epoch": 1.48,
+      "eval_exact_match": 56.64143803216651,
+      "eval_f1": 74.03120203258294,
+      "step": 8100
+    },
+    {
+      "epoch": 1.53,
+      "eval_exact_match": 56.84011352885525,
+      "eval_f1": 74.3235867027388,
+      "step": 8400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.1276207839562443e-05,
+      "loss": 1.2482,
+      "step": 8500
+    },
+    {
+      "epoch": 1.59,
+      "eval_exact_match": 57.28476821192053,
+      "eval_f1": 74.36995381137226,
+      "step": 8700
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.997265268915224e-06,
+      "loss": 1.2677,
+      "step": 9000
+    },
+    {
+      "epoch": 1.64,
+      "eval_exact_match": 57.17123935666982,
+      "eval_f1": 74.31360595646503,
+      "step": 9000
+    },
+    {
+      "epoch": 1.7,
+      "eval_exact_match": 56.9914853358562,
+      "eval_f1": 74.27345402299513,
+      "step": 9300
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 6.7183226982680034e-06,
+      "loss": 1.257,
+      "step": 9500
+    },
+    {
+      "epoch": 1.75,
+      "eval_exact_match": 56.80227057710501,
+      "eval_f1": 74.05651657911156,
+      "step": 9600
+    },
+    {
+      "epoch": 1.8,
+      "eval_exact_match": 57.05771050141911,
+      "eval_f1": 74.23683269095346,
+      "step": 9900
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.448495897903373e-06,
+      "loss": 1.2459,
+      "step": 10000
+    },
+    {
+      "epoch": 1.86,
+      "eval_exact_match": 57.237464522232735,
+      "eval_f1": 74.29842936518452,
+      "step": 10200
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.169553327256153e-06,
+      "loss": 1.2465,
+      "step": 10500
+    },
+    {
+      "epoch": 1.91,
+      "eval_exact_match": 57.17123935666982,
+      "eval_f1": 74.35402701072998,
+      "step": 10500
+    },
+    {
+      "epoch": 1.97,
+      "eval_exact_match": 57.142857142857146,
+      "eval_f1": 74.2724134993522,
+      "step": 10800
+    },
+    {
+      "epoch": 2.0,
+      "step": 10970,
+      "total_flos": 2544773915225664.0,
+      "train_loss": 1.524520064486953,
+      "train_runtime": 1743.0774,
+      "train_samples_per_second": 100.681,
+      "train_steps_per_second": 6.293
+    }
+  ],
+  "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 sha256:01e14d27f23e12c5dde9519de52f275f8a47fba2c872f7c1f8dd2204332a57d6
+size 3515