upload

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9505766062602965,
+    "eval_loss": 0.32655519247055054,
+    "eval_runtime": 25.1958,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 216.822,
+    "eval_steps_per_second": 3.413,
+    "train_loss": 0.06516272406001668,
+    "train_runtime": 4563.7862,
+    "train_samples": 104743,
+    "train_samples_per_second": 229.509,
+    "train_steps_per_second": 1.196
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/electra-large-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "embedding_size": 1024,
+  "finetuning_task": "qnli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9505766062602965,
+    "eval_loss": 0.32655519247055054,
+    "eval_runtime": 25.1958,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 216.822,
+    "eval_steps_per_second": 3.413
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff4ef54bc927757ec408f3fb9cba5548215b9df54bcff32a40b56bfd5b316af
+size 1340745297

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-large-discriminator"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.06516272406001668,
+    "train_runtime": 4563.7862,
+    "train_samples": 104743,
+    "train_samples_per_second": 229.509,
+    "train_steps_per_second": 1.196
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 5460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.816849816849817e-05,
+      "loss": 0.2492,
+      "step": 500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.633699633699634e-05,
+      "loss": 0.15,
+      "step": 1000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.4505494505494506e-05,
+      "loss": 0.0983,
+      "step": 1500
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.2673992673992674e-05,
+      "loss": 0.0631,
+      "step": 2000
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 1.0842490842490842e-05,
+      "loss": 0.0463,
+      "step": 2500
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 9.010989010989011e-06,
+      "loss": 0.0351,
+      "step": 3000
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 0.0247,
+      "step": 3500
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 5.347985347985348e-06,
+      "loss": 0.0165,
+      "step": 4000
+    },
+    {
+      "epoch": 8.24,
+      "learning_rate": 3.516483516483517e-06,
+      "loss": 0.0125,
+      "step": 4500
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 1.6849816849816852e-06,
+      "loss": 0.0094,
+      "step": 5000
+    },
+    {
+      "epoch": 10.0,
+      "step": 5460,
+      "total_flos": 2.6959857790413312e+17,
+      "train_loss": 0.06516272406001668,
+      "train_runtime": 4563.7862,
+      "train_samples_per_second": 229.509,
+      "train_steps_per_second": 1.196
+    }
+  ],
+  "max_steps": 5460,
+  "num_train_epochs": 10,
+  "total_flos": 2.6959857790413312e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b43a6e841dec153b094963d834afb93302290f32d58514c5c527396f3789a91
+size 2479