Upload 11 files

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "./models/portuguese_diff_cse",
+  "architectures": [
+    "BertForCL"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.2.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

eval_results.txt

@@ -0,0 +1,2 @@
+epoch = 2.0
+eval_stsb_spearman = 0.9955015182117884

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc03e195d704961a6901dcf3f9f2b9fab176e1a8d03fd66bcc59033e32fa9046
+size 1752475211

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:501f6fc436c01812ac214093738d0a3abf648c6c528614eb37e3ab49c0f9b3c6
+size 1236084368

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e606b8aa8d5c49237bb38368639a476285e14d1fff4a86e2966fec9c0e8393c
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "do_lower_case": false,
+  "unk_token": "[UNK]",
+  "sep_token": "[SEP]",
+  "pad_token": "[PAD]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "tokenize_chinese_chars": true,
+  "strip_accents": null,
+  "special_tokens_map_file": "/home/user/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
+  "name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "do_basic_tokenize": true,
+  "never_split": null,
+  "model_max_length": 512
+}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 2.0
+train_runtime = 507.537
+train_samples_per_second = 0.859

trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.9955015182117884,
+  "best_model_checkpoint": "./models/portuguese_diff_cse",
+  "epoch": 2.0,
+  "global_step": 436,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "electra_acc": 0.1145,
+      "electra_fix_acc": 0.8984,
+      "electra_rep_acc": 0.0633,
+      "epoch": 0.0,
+      "learning_rate": 6.98394495412844e-06,
+      "loss": 0.3321,
+      "neg_sim": -0.0092,
+      "pos_sim": 0.548,
+      "step": 1
+    },
+    {
+      "epoch": 0.57,
+      "eval_stsb_spearman": 0.9955015182117884,
+      "step": 125
+    },
+    {
+      "epoch": 1.15,
+      "eval_stsb_spearman": 0.9947652924624643,
+      "step": 250
+    },
+    {
+      "epoch": 1.72,
+      "eval_stsb_spearman": 0.9947550447251673,
+      "step": 375
+    },
+    {
+      "epoch": 2.0,
+      "step": 436,
+      "train_runtime": 507.537,
+      "train_samples_per_second": 0.859
+    }
+  ],
+  "max_steps": 436,
+  "num_train_epochs": 2,
+  "total_flos": 6073324447075440,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1816d65ce9a3b787746a59bf2dd9636afab4c6a81d1cd507141fba56da3070d9
+size 2031