initial upload

all_results.json

@@ -0,0 +1,25 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.875,
+    "eval_combined_score": 0.8933058925476604,
+    "eval_f1": 0.9116117850953207,
+    "eval_loss": 0.6050645709037781,
+    "eval_mem_cpu_alloc_delta": 3817472,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 34643456,
+    "eval_runtime": 2.853,
+    "eval_samples": 408,
+    "eval_samples_per_second": 143.007,
+    "init_mem_cpu_alloc_delta": 3205906432,
+    "init_mem_cpu_peaked_delta": 319905792,
+    "init_mem_gpu_alloc_delta": 439072256,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 85659648,
+    "train_mem_cpu_peaked_delta": 187248640,
+    "train_mem_gpu_alloc_delta": 1378346496,
+    "train_mem_gpu_peaked_delta": 3560739840,
+    "train_runtime": 503.0994,
+    "train_samples": 3668,
+    "train_samples_per_second": 1.6
+}

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": "mrpc",
+  "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 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.875,
+    "eval_combined_score": 0.8933058925476604,
+    "eval_f1": 0.9116117850953207,
+    "eval_loss": 0.6050645709037781,
+    "eval_mem_cpu_alloc_delta": 3817472,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 34643456,
+    "eval_runtime": 2.853,
+    "eval_samples": 408,
+    "eval_samples_per_second": 143.007
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3554d3d7b354e139b3248a325dd4a0448fc7eb9ebdbfa92710ca48ea0e1bb592
+size 438023629

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": 3205906432,
+    "init_mem_cpu_peaked_delta": 319905792,
+    "init_mem_gpu_alloc_delta": 439072256,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 85659648,
+    "train_mem_cpu_peaked_delta": 187248640,
+    "train_mem_gpu_alloc_delta": 1378346496,
+    "train_mem_gpu_peaked_delta": 3560739840,
+    "train_runtime": 503.0994,
+    "train_samples": 3668,
+    "train_samples_per_second": 1.6
+}

trainer_state.json

@@ -0,0 +1,29 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "global_step": 805,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.35,
+      "learning_rate": 7.577639751552796e-06,
+      "loss": 0.2682,
+      "step": 500
+    },
+    {
+      "epoch": 7.0,
+      "step": 805,
+      "total_flos": 2158929011656704.0,
+      "train_runtime": 503.0994,
+      "train_samples_per_second": 1.6
+    }
+  ],
+  "max_steps": 805,
+  "num_train_epochs": 7,
+  "total_flos": 2158929011656704.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:844d0f15f00223a28af3ba32270ee1c0cecf7298b9839fee7f256bdff7f46e0f
+size 2415