model

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/gpfs/projects/bsc88/projects/catalan_evaluation/models/roberta-large-ca-v2",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "paraf",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "No Parafrasis",
+    "1": "Parafrasis"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "No Parafrasis": 0,
+    "Parafrasis": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a4b62f251baff1449d840251b3bd5691c06f1b83570d030c5063a2bb1289a2
+size 1421600941

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 @@
+{"errors": "replace", "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"}, "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"}, "unk_token": {"content": "<unk>", "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"}, "add_prefix_space": true, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "/gpfs/projects/bsc88/projects/catalan_evaluation/models/roberta-large-ca-v2", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.8438365477338476,
+  "best_model_checkpoint": "output/roberta-large-ca-v2/parafraseja.py_8_0.00005_date_22-10-14_time_16-03-07/checkpoint-4995",
+  "epoch": 5.0,
+  "global_step": 4995,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 0.5335,
+      "step": 999
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.836,
+      "eval_combined_score": 0.8360819180819181,
+      "eval_f1": 0.8361638361638362,
+      "eval_loss": 0.39040425419807434,
+      "eval_runtime": 58.4758,
+      "eval_samples_per_second": 34.202,
+      "eval_steps_per_second": 2.138,
+      "step": 999
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.3403,
+      "step": 1998
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.832,
+      "eval_combined_score": 0.8342083739045765,
+      "eval_f1": 0.8364167478091529,
+      "eval_loss": 0.4153313934803009,
+      "eval_runtime": 58.4308,
+      "eval_samples_per_second": 34.229,
+      "eval_steps_per_second": 2.139,
+      "step": 1998
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2e-05,
+      "loss": 0.2345,
+      "step": 2997
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8405,
+      "eval_combined_score": 0.8427098930481283,
+      "eval_f1": 0.8449197860962566,
+      "eval_loss": 0.4383120834827423,
+      "eval_runtime": 58.4693,
+      "eval_samples_per_second": 34.206,
+      "eval_steps_per_second": 2.138,
+      "step": 2997
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1e-05,
+      "loss": 0.1644,
+      "step": 3996
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.836,
+      "eval_combined_score": 0.8401272554605888,
+      "eval_f1": 0.8442545109211776,
+      "eval_loss": 0.6573591828346252,
+      "eval_runtime": 58.3674,
+      "eval_samples_per_second": 34.266,
+      "eval_steps_per_second": 2.142,
+      "step": 3996
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.1097,
+      "step": 4995
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.841,
+      "eval_combined_score": 0.8438365477338476,
+      "eval_f1": 0.8466730954676953,
+      "eval_loss": 0.7086848616600037,
+      "eval_runtime": 58.3516,
+      "eval_samples_per_second": 34.275,
+      "eval_steps_per_second": 2.142,
+      "step": 4995
+    },
+    {
+      "epoch": 5.0,
+      "step": 4995,
+      "total_flos": 7.447995455717376e+16,
+      "train_loss": 0.27648499787629427,
+      "train_runtime": 7079.06,
+      "train_samples_per_second": 11.29,
+      "train_steps_per_second": 0.706
+    }
+  ],
+  "max_steps": 4995,
+  "num_train_epochs": 5,
+  "total_flos": 7.447995455717376e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed676d440a87f46a5079e293c785b21237a9713d0cff8bae8bac8bdb041c102
+size 3119