adding model finetuned on sqac

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 59.17381974248927,
+    "eval_f1": 76.26399788082415,
+    "eval_samples": 2082,
+    "train_loss": 0.9321928299920408,
+    "train_runtime": 372.7049,
+    "train_samples": 16598,
+    "train_samples_per_second": 133.602,
+    "train_steps_per_second": 8.355
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "dccuchile/albert-base-8-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": 8,
+  "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": 3.0,
+    "eval_exact_match": 59.17381974248927,
+    "eval_f1": 76.26399788082415,
+    "eval_samples": 2082
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df9a0d7a51e3530c3383abfaaa38951b55875d129f98b79abb9e993fce3bd51
+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-8-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": 3.0,
+    "train_loss": 0.9321928299920408,
+    "train_runtime": 372.7049,
+    "train_samples": 16598,
+    "train_samples_per_second": 133.602,
+    "train_steps_per_second": 8.355
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": 76.26399788082415,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/sqac/albeto_base_8/epochs_3_bs_16_lr_5e-5/checkpoint-2000",
+  "epoch": 3.0,
+  "global_step": 3114,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_exact_match": 38.8412017167382,
+      "eval_f1": 59.56507187901322,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "eval_exact_match": 45.11802575107296,
+      "eval_f1": 66.94860285103326,
+      "step": 400
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.203596660244059e-05,
+      "loss": 2.1132,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "eval_exact_match": 51.663090128755364,
+      "eval_f1": 70.0320493826151,
+      "step": 600
+    },
+    {
+      "epoch": 0.77,
+      "eval_exact_match": 53.59442060085837,
+      "eval_f1": 72.38853344284765,
+      "step": 800
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.400770712909441e-05,
+      "loss": 1.2927,
+      "step": 1000
+    },
+    {
+      "epoch": 0.96,
+      "eval_exact_match": 55.63304721030043,
+      "eval_f1": 74.55898999725306,
+      "step": 1000
+    },
+    {
+      "epoch": 1.16,
+      "eval_exact_match": 56.223175965665234,
+      "eval_f1": 74.4642823357856,
+      "step": 1200
+    },
+    {
+      "epoch": 1.35,
+      "eval_exact_match": 54.98927038626609,
+      "eval_f1": 73.49170360943472,
+      "step": 1400
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.5979447655748235e-05,
+      "loss": 0.8019,
+      "step": 1500
+    },
+    {
+      "epoch": 1.54,
+      "eval_exact_match": 55.9549356223176,
+      "eval_f1": 74.65040749842683,
+      "step": 1600
+    },
+    {
+      "epoch": 1.73,
+      "eval_exact_match": 57.457081545064376,
+      "eval_f1": 75.3556762232775,
+      "step": 1800
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.7951188182402056e-05,
+      "loss": 0.7301,
+      "step": 2000
+    },
+    {
+      "epoch": 1.93,
+      "eval_exact_match": 59.17381974248927,
+      "eval_f1": 76.26399788082415,
+      "step": 2000
+    },
+    {
+      "epoch": 2.12,
+      "eval_exact_match": 57.8862660944206,
+      "eval_f1": 75.18740187093938,
+      "step": 2200
+    },
+    {
+      "epoch": 2.31,
+      "eval_exact_match": 57.77896995708154,
+      "eval_f1": 75.37580137031661,
+      "step": 2400
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 9.922928709055877e-06,
+      "loss": 0.4301,
+      "step": 2500
+    },
+    {
+      "epoch": 2.5,
+      "eval_exact_match": 58.31545064377682,
+      "eval_f1": 75.85451949985745,
+      "step": 2600
+    },
+    {
+      "epoch": 2.7,
+      "eval_exact_match": 57.18884120171674,
+      "eval_f1": 75.28315608222837,
+      "step": 2800
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.8946692357096983e-06,
+      "loss": 0.3568,
+      "step": 3000
+    },
+    {
+      "epoch": 2.89,
+      "eval_exact_match": 57.832618025751074,
+      "eval_f1": 75.7745668972737,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "step": 3114,
+      "total_flos": 1075319724912768.0,
+      "train_loss": 0.9321928299920408,
+      "train_runtime": 372.7049,
+      "train_samples_per_second": 133.602,
+      "train_steps_per_second": 8.355
+    }
+  ],
+  "max_steps": 3114,
+  "num_train_epochs": 3,
+  "total_flos": 1075319724912768.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f472e8c19e967554b1d18d4530a72fa977bf5ece6b2c029a85deb6e84552d0
+size 3515