adding model finetuned on sqac

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 60.89055793991416,
+    "eval_f1": 78.34967086796246,
+    "eval_samples": 2082,
+    "train_loss": 0.7222001878742078,
+    "train_runtime": 561.1755,
+    "train_samples": 16598,
+    "train_samples_per_second": 118.309,
+    "train_steps_per_second": 7.399
+}

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": 4.0,
+    "eval_exact_match": 60.89055793991416,
+    "eval_f1": 78.34967086796246,
+    "eval_samples": 2082
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ffab714514c261d250c23aa6915042835b8dafdf21c7c2e7e46e50e2d4c9833
+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": 4.0,
+    "train_loss": 0.7222001878742078,
+    "train_runtime": 561.1755,
+    "train_samples": 16598,
+    "train_samples_per_second": 118.309,
+    "train_steps_per_second": 7.399
+}

trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 78.34967086796246,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/sqac/albeto_base_10/epochs_4_bs_16_lr_5e-5/checkpoint-2400",
+  "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": 39.91416309012875,
+      "eval_f1": 61.87011148809531,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "eval_exact_match": 49.0343347639485,
+      "eval_f1": 70.88566620873883,
+      "step": 400
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.4039017341040465e-05,
+      "loss": 2.0371,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "eval_exact_match": 52.78969957081545,
+      "eval_f1": 71.57893724017156,
+      "step": 600
+    },
+    {
+      "epoch": 0.77,
+      "eval_exact_match": 54.02360515021459,
+      "eval_f1": 73.13986921785923,
+      "step": 800
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.8017822736030825e-05,
+      "loss": 1.1955,
+      "step": 1000
+    },
+    {
+      "epoch": 0.96,
+      "eval_exact_match": 56.652360515021456,
+      "eval_f1": 76.14245779632923,
+      "step": 1000
+    },
+    {
+      "epoch": 1.16,
+      "eval_exact_match": 58.53004291845494,
+      "eval_f1": 76.18238309482629,
+      "step": 1200
+    },
+    {
+      "epoch": 1.35,
+      "eval_exact_match": 57.34978540772532,
+      "eval_f1": 76.44989686902251,
+      "step": 1400
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.200867052023121e-05,
+      "loss": 0.7733,
+      "step": 1500
+    },
+    {
+      "epoch": 1.54,
+      "eval_exact_match": 57.40343347639485,
+      "eval_f1": 76.46366543573856,
+      "step": 1600
+    },
+    {
+      "epoch": 1.73,
+      "eval_exact_match": 58.36909871244635,
+      "eval_f1": 76.59404135981585,
+      "step": 1800
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2.5987475915221583e-05,
+      "loss": 0.7258,
+      "step": 2000
+    },
+    {
+      "epoch": 1.93,
+      "eval_exact_match": 60.08583690987125,
+      "eval_f1": 77.4052301190737,
+      "step": 2000
+    },
+    {
+      "epoch": 2.12,
+      "eval_exact_match": 60.51502145922747,
+      "eval_f1": 77.871672236987,
+      "step": 2200
+    },
+    {
+      "epoch": 2.31,
+      "eval_exact_match": 60.89055793991416,
+      "eval_f1": 78.34967086796246,
+      "step": 2400
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.996628131021195e-05,
+      "loss": 0.4385,
+      "step": 2500
+    },
+    {
+      "epoch": 2.5,
+      "eval_exact_match": 59.76394849785408,
+      "eval_f1": 77.37556959755096,
+      "step": 2600
+    },
+    {
+      "epoch": 2.7,
+      "eval_exact_match": 60.24678111587983,
+      "eval_f1": 78.10117865142247,
+      "step": 2800
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.3945086705202311e-05,
+      "loss": 0.3857,
+      "step": 3000
+    },
+    {
+      "epoch": 2.89,
+      "eval_exact_match": 59.817596566523605,
+      "eval_f1": 78.32500495296635,
+      "step": 3000
+    },
+    {
+      "epoch": 3.08,
+      "eval_exact_match": 59.97854077253219,
+      "eval_f1": 78.28655798822736,
+      "step": 3200
+    },
+    {
+      "epoch": 3.28,
+      "eval_exact_match": 59.12017167381974,
+      "eval_f1": 77.37073661729056,
+      "step": 3400
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 7.923892100192678e-06,
+      "loss": 0.2275,
+      "step": 3500
+    },
+    {
+      "epoch": 3.47,
+      "eval_exact_match": 59.33476394849785,
+      "eval_f1": 77.38568317713487,
+      "step": 3600
+    },
+    {
+      "epoch": 3.66,
+      "eval_exact_match": 58.95922746781116,
+      "eval_f1": 77.35370183854889,
+      "step": 3800
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.9026974951830444e-06,
+      "loss": 0.1611,
+      "step": 4000
+    },
+    {
+      "epoch": 3.85,
+      "eval_exact_match": 59.92489270386266,
+      "eval_f1": 77.79068599835692,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "step": 4152,
+      "total_flos": 1433973109980672.0,
+      "train_loss": 0.7222001878742078,
+      "train_runtime": 561.1755,
+      "train_samples_per_second": 118.309,
+      "train_steps_per_second": 7.399
+    }
+  ],
+  "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:e46527521b69f1e7d346068d4ee01d59a35a4075d7d230d9f3900c28b88c6688
+size 3515