upload model

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bsc/roberta-base-ca-cased",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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": "4.9.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a32a38e7e90c4cd0f27aa3edb360a6b31f9464e941c11cd700e809db8c3043
+size 501643591

special_tokens_map.json

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 87.74177915473423,
+  "best_model_checkpoint": "/home/ccasimiro/ccasimiro/berta/src/finetuning/qa/roberta-base-ca-cased-qa/viquiquad/checkpoint-3177",
+  "epoch": 10.0,
+  "global_step": 3530,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 70.39517749497655,
+      "eval_f1": 85.15879769695867,
+      "step": 353
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.291784702549575e-05,
+      "loss": 1.2372,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 73.40924313462827,
+      "eval_f1": 87.52377432306103,
+      "step": 706
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 3.58356940509915e-05,
+      "loss": 0.4076,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 72.87340924313463,
+      "eval_f1": 86.86230071137398,
+      "step": 1059
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 72.60549229738781,
+      "eval_f1": 86.9056612129989,
+      "step": 1412
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 2.8753541076487255e-05,
+      "loss": 0.1874,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_exact_match": 73.8780977896852,
+      "eval_f1": 87.61361215231298,
+      "step": 1765
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 2.1671388101983002e-05,
+      "loss": 0.0883,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_exact_match": 72.5385130609511,
+      "eval_f1": 87.16597098547801,
+      "step": 2118
+    },
+    {
+      "epoch": 7.0,
+      "eval_exact_match": 72.94038847957134,
+      "eval_f1": 87.6293952976471,
+      "step": 2471
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 1.4589235127478753e-05,
+      "loss": 0.0449,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_exact_match": 73.07434695244474,
+      "eval_f1": 87.3948843173073,
+      "step": 2824
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 7.507082152974506e-06,
+      "loss": 0.0272,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_exact_match": 73.8780977896852,
+      "eval_f1": 87.74177915473423,
+      "step": 3177
+    },
+    {
+      "epoch": 9.92,
+      "learning_rate": 4.2492917847025503e-07,
+      "loss": 0.0148,
+      "step": 3500
+    },
+    {
+      "epoch": 10.0,
+      "eval_exact_match": 73.54320160750167,
+      "eval_f1": 87.60609812320592,
+      "step": 3530
+    },
+    {
+      "epoch": 10.0,
+      "step": 3530,
+      "total_flos": 2.949256493279232e+16,
+      "train_loss": 0.28446678726936536,
+      "train_runtime": 8024.7966,
+      "train_samples_per_second": 14.065,
+      "train_steps_per_second": 0.44
+    }
+  ],
+  "max_steps": 3530,
+  "num_train_epochs": 10,
+  "total_flos": 2.949256493279232e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38cf4473f5bb03bbe97cdb2f062e5014d7db1c4462119982eb0cc9f4b1d4305
+size 2735