upload model

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.7437504611247936,
+    "eval_loss": 0.33539897203445435,
+    "eval_pearson": 0.7484496954159015,
+    "eval_runtime": 10.2662,
+    "eval_samples": 500,
+    "eval_samples_per_second": 48.704,
+    "eval_spearmanr": 0.7390512268336858,
+    "eval_steps_per_second": 1.559,
+    "predict_combined_score": 0.8155956731804759,
+    "predict_loss": 0.2975914776325226,
+    "predict_pearson": 0.8120486139447483,
+    "predict_runtime": 10.2099,
+    "predict_samples_per_second": 48.972,
+    "predict_spearmanr": 0.8191427324162035,
+    "predict_steps_per_second": 1.567,
+    "train_loss": 0.17999618823711688,
+    "train_runtime": 1715.2897,
+    "train_samples": 2073,
+    "train_samples_per_second": 12.085,
+    "train_steps_per_second": 0.379
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bsc/roberta-base-ca-cased",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": 0.7437504611247936,
+    "eval_loss": 0.33539897203445435,
+    "eval_pearson": 0.7484496954159015,
+    "eval_runtime": 10.2662,
+    "eval_samples": 500,
+    "eval_samples_per_second": 48.704,
+    "eval_spearmanr": 0.7390512268336858,
+    "eval_steps_per_second": 1.559
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cbf9473aa0ddba401a11d0da19747b16e4661908fc403b7073f4088743c5c2a
+size 504004120

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"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.17999618823711688,
+    "train_runtime": 1715.2897,
+    "train_samples": 2073,
+    "train_samples_per_second": 12.085,
+    "train_steps_per_second": 0.379
+}

trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.7437504611247936,
+  "best_model_checkpoint": "/home/ccasimiro/ccasimiro/berta/src/finetuning/sts/roberta-base-ca-cased-sts/checkpoint-455",
+  "epoch": 10.0,
+  "global_step": 650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.6805577619623024,
+      "eval_loss": 0.4414205849170685,
+      "eval_pearson": 0.6667563227309266,
+      "eval_runtime": 10.4961,
+      "eval_samples_per_second": 47.637,
+      "eval_spearmanr": 0.6943592011936784,
+      "eval_steps_per_second": 1.524,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.7152235717947664,
+      "eval_loss": 0.3806273341178894,
+      "eval_pearson": 0.718255308294224,
+      "eval_runtime": 10.3114,
+      "eval_samples_per_second": 48.49,
+      "eval_spearmanr": 0.7121918352953086,
+      "eval_steps_per_second": 1.552,
+      "step": 130
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.7127492106541832,
+      "eval_loss": 0.3876854479312897,
+      "eval_pearson": 0.7141017567917686,
+      "eval_runtime": 10.3161,
+      "eval_samples_per_second": 48.468,
+      "eval_spearmanr": 0.7113966645165978,
+      "eval_steps_per_second": 1.551,
+      "step": 195
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.7300156062557066,
+      "eval_loss": 0.380470871925354,
+      "eval_pearson": 0.731967198769625,
+      "eval_runtime": 10.2905,
+      "eval_samples_per_second": 48.589,
+      "eval_spearmanr": 0.7280640137417881,
+      "eval_steps_per_second": 1.555,
+      "step": 260
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.7302656118713525,
+      "eval_loss": 0.33833837509155273,
+      "eval_pearson": 0.7366071674449775,
+      "eval_runtime": 10.3827,
+      "eval_samples_per_second": 48.157,
+      "eval_spearmanr": 0.7239240562977276,
+      "eval_steps_per_second": 1.541,
+      "step": 325
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.7325772109724351,
+      "eval_loss": 0.36641925573349,
+      "eval_pearson": 0.7349002365451928,
+      "eval_runtime": 10.2668,
+      "eval_samples_per_second": 48.701,
+      "eval_spearmanr": 0.7302541853996775,
+      "eval_steps_per_second": 1.558,
+      "step": 390
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.7437504611247936,
+      "eval_loss": 0.33539897203445435,
+      "eval_pearson": 0.7484496954159015,
+      "eval_runtime": 10.2857,
+      "eval_samples_per_second": 48.611,
+      "eval_spearmanr": 0.7390512268336858,
+      "eval_steps_per_second": 1.556,
+      "step": 455
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 1.153846153846154e-05,
+      "loss": 0.2244,
+      "step": 500
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.7370831462161629,
+      "eval_loss": 0.3497055172920227,
+      "eval_pearson": 0.7429713239243328,
+      "eval_runtime": 10.3129,
+      "eval_samples_per_second": 48.483,
+      "eval_spearmanr": 0.731194968507993,
+      "eval_steps_per_second": 1.551,
+      "step": 520
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.7429305671131216,
+      "eval_loss": 0.3452938497066498,
+      "eval_pearson": 0.7476867678468953,
+      "eval_runtime": 10.2732,
+      "eval_samples_per_second": 48.67,
+      "eval_spearmanr": 0.7381743663793479,
+      "eval_steps_per_second": 1.557,
+      "step": 585
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": 0.7410151955266198,
+      "eval_loss": 0.3426874279975891,
+      "eval_pearson": 0.7469684882191953,
+      "eval_runtime": 10.2706,
+      "eval_samples_per_second": 48.683,
+      "eval_spearmanr": 0.7350619028340443,
+      "eval_steps_per_second": 1.558,
+      "step": 650
+    },
+    {
+      "epoch": 10.0,
+      "step": 650,
+      "total_flos": 5454243205724160.0,
+      "train_loss": 0.17999618823711688,
+      "train_runtime": 1715.2897,
+      "train_samples_per_second": 12.085,
+      "train_steps_per_second": 0.379
+    }
+  ],
+  "max_steps": 650,
+  "num_train_epochs": 10,
+  "total_flos": 5454243205724160.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b082c17858e6b0b991611988c93aaae3cc138a67f2ed1507e280b40332e18502
+size 2799