adding model finetuned on sqac

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 54.72103004291846,
+    "eval_f1": 73.16917224867254,
+    "eval_samples": 2082,
+    "train_loss": 0.7790700769148811,
+    "train_runtime": 432.1028,
+    "train_samples": 16598,
+    "train_samples_per_second": 153.649,
+    "train_steps_per_second": 9.609
+}

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": 4.0,
+    "eval_exact_match": 54.72103004291846,
+    "eval_f1": 73.16917224867254,
+    "eval_samples": 2082
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6410de8bb5215e87f68fd496938b60885d61998c9b65a96142c9052c16b997fe
+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": 4.0,
+    "train_loss": 0.7790700769148811,
+    "train_runtime": 432.1028,
+    "train_samples": 16598,
+    "train_samples_per_second": 153.649,
+    "train_steps_per_second": 9.609
+}

trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 73.16917224867254,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/sqac/albeto_base_6/epochs_4_bs_16_lr_5e-5/checkpoint-1800",
+  "epoch": 4.0,
+  "global_step": 4152,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_exact_match": 33.36909871244635,
+      "eval_f1": 54.78264317515576,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "eval_exact_match": 43.50858369098712,
+      "eval_f1": 63.86348098660957,
+      "step": 400
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.4014932562620424e-05,
+      "loss": 2.2717,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "eval_exact_match": 48.22961373390558,
+      "eval_f1": 67.33109541594044,
+      "step": 600
+    },
+    {
+      "epoch": 0.77,
+      "eval_exact_match": 51.3412017167382,
+      "eval_f1": 70.04063336916818,
+      "step": 800
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.799373795761079e-05,
+      "loss": 1.3831,
+      "step": 1000
+    },
+    {
+      "epoch": 0.96,
+      "eval_exact_match": 51.44849785407725,
+      "eval_f1": 70.96531020638378,
+      "step": 1000
+    },
+    {
+      "epoch": 1.16,
+      "eval_exact_match": 52.73605150214592,
+      "eval_f1": 71.04868788055973,
+      "step": 1200
+    },
+    {
+      "epoch": 1.35,
+      "eval_exact_match": 52.78969957081545,
+      "eval_f1": 71.7028117298826,
+      "step": 1400
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.197254335260116e-05,
+      "loss": 0.848,
+      "step": 1500
+    },
+    {
+      "epoch": 1.54,
+      "eval_exact_match": 53.80901287553648,
+      "eval_f1": 72.80035261141751,
+      "step": 1600
+    },
+    {
+      "epoch": 1.73,
+      "eval_exact_match": 54.72103004291846,
+      "eval_f1": 73.16917224867254,
+      "step": 1800
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2.5951348747591525e-05,
+      "loss": 0.7974,
+      "step": 2000
+    },
+    {
+      "epoch": 1.93,
+      "eval_exact_match": 55.36480686695279,
+      "eval_f1": 72.84567287023638,
+      "step": 2000
+    },
+    {
+      "epoch": 2.12,
+      "eval_exact_match": 53.80901287553648,
+      "eval_f1": 71.49884589693431,
+      "step": 2200
+    },
+    {
+      "epoch": 2.31,
+      "eval_exact_match": 53.862660944206006,
+      "eval_f1": 72.42435834140822,
+      "step": 2400
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9930154142581888e-05,
+      "loss": 0.4397,
+      "step": 2500
+    },
+    {
+      "epoch": 2.5,
+      "eval_exact_match": 53.91630901287554,
+      "eval_f1": 72.01940673830065,
+      "step": 2600
+    },
+    {
+      "epoch": 2.7,
+      "eval_exact_match": 54.18454935622318,
+      "eval_f1": 72.42131954627004,
+      "step": 2800
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.3908959537572255e-05,
+      "loss": 0.3679,
+      "step": 3000
+    },
+    {
+      "epoch": 2.89,
+      "eval_exact_match": 53.648068669527895,
+      "eval_f1": 72.24358443143393,
+      "step": 3000
+    },
+    {
+      "epoch": 3.08,
+      "eval_exact_match": 53.16523605150215,
+      "eval_f1": 71.85180232237707,
+      "step": 3200
+    },
+    {
+      "epoch": 3.28,
+      "eval_exact_match": 53.701716738197426,
+      "eval_f1": 71.87041699024132,
+      "step": 3400
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 7.88776493256262e-06,
+      "loss": 0.1905,
+      "step": 3500
+    },
+    {
+      "epoch": 3.47,
+      "eval_exact_match": 53.37982832618026,
+      "eval_f1": 71.85913435306477,
+      "step": 3600
+    },
+    {
+      "epoch": 3.66,
+      "eval_exact_match": 53.21888412017167,
+      "eval_f1": 71.95656973845054,
+      "step": 3800
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.8665703275529866e-06,
+      "loss": 0.1273,
+      "step": 4000
+    },
+    {
+      "epoch": 3.85,
+      "eval_exact_match": 52.84334763948498,
+      "eval_f1": 71.60301657985642,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "step": 4152,
+      "total_flos": 1433973109980672.0,
+      "train_loss": 0.7790700769148811,
+      "train_runtime": 432.1028,
+      "train_samples_per_second": 153.649,
+      "train_steps_per_second": 9.609
+    }
+  ],
+  "max_steps": 4152,
+  "num_train_epochs": 4,
+  "total_flos": 1433973109980672.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00493d6b77205d3eb855f8e41662b3381bdaa17557c65727b5b12b3b0afe4088
+size 3515