initial update

all_results.json

@@ -0,0 +1,25 @@
+{
+    "epoch": 7.0,
+    "eval_combined_score": 0.9032626125657692,
+    "eval_loss": 0.4479755759239197,
+    "eval_mem_cpu_alloc_delta": 4677632,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 34652672,
+    "eval_pearson": 0.9040208006147256,
+    "eval_runtime": 10.926,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 137.287,
+    "eval_spearmanr": 0.9025044245168129,
+    "init_mem_cpu_alloc_delta": 3210498048,
+    "init_mem_cpu_peaked_delta": 319852544,
+    "init_mem_gpu_alloc_delta": 439069184,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 86511616,
+    "train_mem_cpu_peaked_delta": 187301888,
+    "train_mem_gpu_alloc_delta": 1378340352,
+    "train_mem_gpu_peaked_delta": 3560736768,
+    "train_runtime": 851.9812,
+    "train_samples": 5749,
+    "train_samples_per_second": 1.479
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "finetuning_task": "stsb",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.6.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_combined_score": 0.9032626125657692,
+    "eval_loss": 0.4479755759239197,
+    "eval_mem_cpu_alloc_delta": 4677632,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 34652672,
+    "eval_pearson": 0.9040208006147256,
+    "eval_runtime": 10.926,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 137.287,
+    "eval_spearmanr": 0.9025044245168129
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d6b7312e51a01be1522e1e54bd16a54b92060f5157974ab399115ab739a475
+size 438020562

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 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-base-discriminator"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "init_mem_cpu_alloc_delta": 3210498048,
+    "init_mem_cpu_peaked_delta": 319852544,
+    "init_mem_gpu_alloc_delta": 439069184,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 86511616,
+    "train_mem_cpu_peaked_delta": 187301888,
+    "train_mem_gpu_alloc_delta": 1378340352,
+    "train_mem_gpu_peaked_delta": 3560736768,
+    "train_runtime": 851.9812,
+    "train_samples": 5749,
+    "train_samples_per_second": 1.479
+}

trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "global_step": 1260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.2063492063492064e-05,
+      "loss": 0.7453,
+      "step": 500
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 4.126984126984127e-06,
+      "loss": 0.1724,
+      "step": 1000
+    },
+    {
+      "epoch": 7.0,
+      "step": 1260,
+      "total_flos": 3383750193551616.0,
+      "train_runtime": 851.9812,
+      "train_samples_per_second": 1.479
+    }
+  ],
+  "max_steps": 1260,
+  "num_train_epochs": 7,
+  "total_flos": 3383750193551616.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f7f48622be806e85e1a11e455cb41674d7cabec8609077f25629be2c2b78cd4
+size 2415