adding model finetuned on sqac

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 63.62660944206009,
+    "eval_f1": 80.94744810096695,
+    "eval_samples": 2077,
+    "train_loss": 0.6470010164663219,
+    "train_runtime": 876.8981,
+    "train_samples": 16548,
+    "train_samples_per_second": 56.613,
+    "train_steps_per_second": 3.541
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 3.0,
+    "eval_exact_match": 63.62660944206009,
+    "eval_f1": 80.94744810096695,
+    "eval_samples": 2077
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2287e49959dfc7614688c1136a813c6c9e9752d62b14b773027224946f5ba8de
+size 496288177

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_len": 512,
+  "name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6470010164663219,
+    "train_runtime": 876.8981,
+    "train_samples": 16548,
+    "train_samples_per_second": 56.613,
+    "train_steps_per_second": 3.541
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": 80.94744810096695,
+  "best_model_checkpoint": "/home/jcanete/ft-data/all_results/sqac/roberta_base_bne/epochs_3_bs_16_lr_3e-5/checkpoint-2000",
+  "epoch": 3.0,
+  "global_step": 3105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_exact_match": 47.532188841201716,
+      "eval_f1": 69.33897723912453,
+      "step": 200
+    },
+    {
+      "epoch": 0.39,
+      "eval_exact_match": 53.862660944206006,
+      "eval_f1": 73.09612890375904,
+      "step": 400
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.518840579710145e-05,
+      "loss": 1.7311,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "eval_exact_match": 56.33047210300429,
+      "eval_f1": 76.36054486750021,
+      "step": 600
+    },
+    {
+      "epoch": 0.77,
+      "eval_exact_match": 59.17381974248927,
+      "eval_f1": 78.2471790298137,
+      "step": 800
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.0357487922705316e-05,
+      "loss": 1.0008,
+      "step": 1000
+    },
+    {
+      "epoch": 0.97,
+      "eval_exact_match": 62.82188841201717,
+      "eval_f1": 79.9716859895811,
+      "step": 1000
+    },
+    {
+      "epoch": 1.16,
+      "eval_exact_match": 62.1244635193133,
+      "eval_f1": 79.20024477578876,
+      "step": 1200
+    },
+    {
+      "epoch": 1.35,
+      "eval_exact_match": 63.09012875536481,
+      "eval_f1": 80.33927406223063,
+      "step": 1400
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.552657004830918e-05,
+      "loss": 0.5026,
+      "step": 1500
+    },
+    {
+      "epoch": 1.55,
+      "eval_exact_match": 62.28540772532189,
+      "eval_f1": 79.52570777544153,
+      "step": 1600
+    },
+    {
+      "epoch": 1.74,
+      "eval_exact_match": 62.607296137339056,
+      "eval_f1": 80.02469983579446,
+      "step": 1800
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.0695652173913044e-05,
+      "loss": 0.4535,
+      "step": 2000
+    },
+    {
+      "epoch": 1.93,
+      "eval_exact_match": 63.62660944206009,
+      "eval_f1": 80.94744810096695,
+      "step": 2000
+    },
+    {
+      "epoch": 2.13,
+      "eval_exact_match": 63.09012875536481,
+      "eval_f1": 80.42628565826091,
+      "step": 2200
+    },
+    {
+      "epoch": 2.32,
+      "eval_exact_match": 63.358369098712444,
+      "eval_f1": 80.76418115011096,
+      "step": 2400
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 5.864734299516909e-06,
+      "loss": 0.1763,
+      "step": 2500
+    },
+    {
+      "epoch": 2.51,
+      "eval_exact_match": 62.92918454935622,
+      "eval_f1": 80.63880344911603,
+      "step": 2600
+    },
+    {
+      "epoch": 2.71,
+      "eval_exact_match": 62.98283261802575,
+      "eval_f1": 80.47469561336324,
+      "step": 2800
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.033816425120773e-06,
+      "loss": 0.1245,
+      "step": 3000
+    },
+    {
+      "epoch": 2.9,
+      "eval_exact_match": 64.05579399141631,
+      "eval_f1": 80.84469008915202,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "step": 3105,
+      "total_flos": 1.2663698322068352e+16,
+      "train_loss": 0.6470010164663219,
+      "train_runtime": 876.8981,
+      "train_samples_per_second": 56.613,
+      "train_steps_per_second": 3.541
+    }
+  ],
+  "max_steps": 3105,
+  "num_train_epochs": 3,
+  "total_flos": 1.2663698322068352e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbedb04449556244bc26a8a97a6cf9e9e7d0873a79855f8010c9413b491ff1f8
+size 3439