Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9541284403669725,
+    "eval_loss": 0.18563394248485565,
+    "eval_runtime": 3.5006,
+    "eval_samples": 872,
+    "eval_samples_per_second": 249.103,
+    "eval_steps_per_second": 31.138,
+    "train_loss": 0.06732057612185807,
+    "train_runtime": 7753.7046,
+    "train_samples": 67349,
+    "train_samples_per_second": 86.86,
+    "train_steps_per_second": 2.715
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_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",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.9.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9541284403669725,
+    "eval_loss": 0.18563394248485565,
+    "eval_runtime": 3.5006,
+    "eval_samples": 872,
+    "eval_samples_per_second": 249.103,
+    "eval_steps_per_second": 31.138
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29bf1680e31ba71f0682a4f533b110736ed3f07f972ffa57d04edf7344dd8fd6
+size 438020461

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", "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.06732057612185807,
+    "train_runtime": 7753.7046,
+    "train_samples": 67349,
+    "train_samples_per_second": 86.86,
+    "train_steps_per_second": 2.715
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.9541284403669725,
+  "best_model_checkpoint": "./electra-base-discriminator/fine_tuned_models/checkpoint-8420",
+  "epoch": 10.0,
+  "global_step": 21050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8398562688161604e-05,
+      "loss": 0.228,
+      "step": 2105
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9426605504587156,
+      "eval_loss": 0.19972862303256989,
+      "eval_runtime": 3.5276,
+      "eval_samples_per_second": 247.196,
+      "eval_steps_per_second": 30.9,
+      "step": 2105
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6354277945032536e-05,
+      "loss": 0.1181,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.948394495412844,
+      "eval_loss": 0.19976772367954254,
+      "eval_runtime": 3.5381,
+      "eval_samples_per_second": 246.462,
+      "eval_steps_per_second": 30.808,
+      "step": 4210
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.4309993201903469e-05,
+      "loss": 0.0879,
+      "step": 6315
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9461009174311926,
+      "eval_loss": 0.2184586375951767,
+      "eval_runtime": 3.5293,
+      "eval_samples_per_second": 247.074,
+      "eval_steps_per_second": 30.884,
+      "step": 6315
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2265708458774402e-05,
+      "loss": 0.0671,
+      "step": 8420
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9541284403669725,
+      "eval_loss": 0.18563394248485565,
+      "eval_runtime": 3.533,
+      "eval_samples_per_second": 246.815,
+      "eval_steps_per_second": 30.852,
+      "step": 8420
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.0221423715645335e-05,
+      "loss": 0.0512,
+      "step": 10525
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9472477064220184,
+      "eval_loss": 0.24747443199157715,
+      "eval_runtime": 3.5309,
+      "eval_samples_per_second": 246.965,
+      "eval_steps_per_second": 30.871,
+      "step": 10525
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.177138972516268e-06,
+      "loss": 0.0396,
+      "step": 12630
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.948394495412844,
+      "eval_loss": 0.20705512166023254,
+      "eval_runtime": 3.5235,
+      "eval_samples_per_second": 247.482,
+      "eval_steps_per_second": 30.935,
+      "step": 12630
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.132854229387201e-06,
+      "loss": 0.0303,
+      "step": 14735
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9461009174311926,
+      "eval_loss": 0.25413599610328674,
+      "eval_runtime": 3.5256,
+      "eval_samples_per_second": 247.331,
+      "eval_steps_per_second": 30.916,
+      "step": 14735
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.088569486258134e-06,
+      "loss": 0.0221,
+      "step": 16840
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9380733944954128,
+      "eval_loss": 0.29228484630584717,
+      "eval_runtime": 3.5294,
+      "eval_samples_per_second": 247.067,
+      "eval_steps_per_second": 30.883,
+      "step": 16840
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.044284743129067e-06,
+      "loss": 0.0173,
+      "step": 18945
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9426605504587156,
+      "eval_loss": 0.32282954454421997,
+      "eval_runtime": 3.5271,
+      "eval_samples_per_second": 247.23,
+      "eval_steps_per_second": 30.904,
+      "step": 18945
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0117,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9461009174311926,
+      "eval_loss": 0.3563162386417389,
+      "eval_runtime": 3.5159,
+      "eval_samples_per_second": 248.017,
+      "eval_steps_per_second": 31.002,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "step": 21050,
+      "total_flos": 2.831471218376448e+16,
+      "train_loss": 0.06732057612185807,
+      "train_runtime": 7753.7046,
+      "train_samples_per_second": 86.86,
+      "train_steps_per_second": 2.715
+    }
+  ],
+  "max_steps": 21050,
+  "num_train_epochs": 10,
+  "total_flos": 2.831471218376448e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40dc78fd1c09e06cdb22791a2b4684b36abeaf5ca83946d972996af2d571cdd4
+size 2671