Upload finetuned model weight

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9518348623853211,
+    "eval_loss": 0.19545245170593262,
+    "eval_runtime": 5.8156,
+    "eval_samples": 872,
+    "eval_samples_per_second": 149.943,
+    "train_runtime": 3417.3067,
+    "train_samples": 67349,
+    "train_samples_per_second": 1.848
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 768,
+  "finetuning_task": "sst2",
+  "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": "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 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9518348623853211,
+    "eval_loss": 0.19545245170593262,
+    "eval_runtime": 5.8156,
+    "eval_samples": 872,
+    "eval_samples_per_second": 149.943
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51f4d737b844c314bb6cfa7e0540b0ecc927dd757b385434e40cd425c644689
+size 438023632

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 +1,6 @@
+{
+    "epoch": 3.0,
+    "train_runtime": 3417.3067,
+    "train_samples": 67349,
+    "train_samples_per_second": 1.848
+}

trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6315,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8416468725257326e-05,
+      "loss": 0.2819,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6832937450514647e-05,
+      "loss": 0.1863,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5249406175771972e-05,
+      "loss": 0.1603,
+      "step": 1500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3665874901029297e-05,
+      "loss": 0.1523,
+      "step": 2000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.208234362628662e-05,
+      "loss": 0.1108,
+      "step": 2500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.0498812351543943e-05,
+      "loss": 0.1091,
+      "step": 3000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.915281076801267e-06,
+      "loss": 0.1132,
+      "step": 3500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.331749802058591e-06,
+      "loss": 0.1071,
+      "step": 4000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 5.748218527315916e-06,
+      "loss": 0.0904,
+      "step": 4500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.164687252573238e-06,
+      "loss": 0.0743,
+      "step": 5000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 2.581155977830562e-06,
+      "loss": 0.0785,
+      "step": 5500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 9.976247030878861e-07,
+      "loss": 0.0701,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "step": 6315,
+      "total_flos": 1.6988827310258688e+16,
+      "train_runtime": 3417.3067,
+      "train_samples_per_second": 1.848
+    }
+  ],
+  "max_steps": 6315,
+  "num_train_epochs": 3,
+  "total_flos": 1.6988827310258688e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7debc14fb8d941ab674057a31544c986565bd75fcd17845ad744eb36e5f4241
+size 2415