Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9380733944954128,
+    "eval_loss": 0.32522284984588623,
+    "eval_runtime": 2.5616,
+    "eval_samples": 872,
+    "eval_samples_per_second": 340.409,
+    "eval_steps_per_second": 42.551,
+    "train_loss": 0.08915798015096126,
+    "train_runtime": 3440.211,
+    "train_samples": 67349,
+    "train_samples_per_second": 195.77,
+    "train_steps_per_second": 6.119
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "xlnet-base-cased",
+  "architectures": [
+    "XLNetForSequenceClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "finetuning_task": "sst2",
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "problem_type": "single_label_classification",
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "transformers_version": "4.9.0.dev0",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9380733944954128,
+    "eval_loss": 0.32522284984588623,
+    "eval_runtime": 2.5616,
+    "eval_samples": 872,
+    "eval_samples_per_second": 340.409,
+    "eval_steps_per_second": 42.551
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b112338d8d9198fb30b4fc396603b9d4b2534a2c2cc5f9fb04be87e5c229371
+size 469316829

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<eop>", "<eod>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<eop>", "<eod>"], "special_tokens_map_file": null, "name_or_path": "xlnet-base-cased", "tokenizer_class": "XLNetTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.08915798015096126,
+    "train_runtime": 3440.211,
+    "train_samples": 67349,
+    "train_samples_per_second": 195.77,
+    "train_steps_per_second": 6.119
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.9380733944954128,
+  "best_model_checkpoint": "./electra-base-discriminator/fine_tuned_models/checkpoint-14735",
+  "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": 0.2696,
+      "step": 2105
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9334862385321101,
+      "eval_loss": 0.20129133760929108,
+      "eval_runtime": 2.0684,
+      "eval_samples_per_second": 421.585,
+      "eval_steps_per_second": 52.698,
+      "step": 2105
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6354277945032536e-05,
+      "loss": 0.1453,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9369266055045872,
+      "eval_loss": 0.23204709589481354,
+      "eval_runtime": 2.4051,
+      "eval_samples_per_second": 362.559,
+      "eval_steps_per_second": 45.32,
+      "step": 4210
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.4309993201903469e-05,
+      "loss": 0.1135,
+      "step": 6315
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.930045871559633,
+      "eval_loss": 0.2923499047756195,
+      "eval_runtime": 2.4212,
+      "eval_samples_per_second": 360.148,
+      "eval_steps_per_second": 45.018,
+      "step": 6315
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2265708458774402e-05,
+      "loss": 0.0906,
+      "step": 8420
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9346330275229358,
+      "eval_loss": 0.32609012722969055,
+      "eval_runtime": 1.9468,
+      "eval_samples_per_second": 447.926,
+      "eval_steps_per_second": 55.991,
+      "step": 8420
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.0221423715645335e-05,
+      "loss": 0.072,
+      "step": 10525
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9288990825688074,
+      "eval_loss": 0.3121407628059387,
+      "eval_runtime": 2.1923,
+      "eval_samples_per_second": 397.751,
+      "eval_steps_per_second": 49.719,
+      "step": 10525
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.177138972516268e-06,
+      "loss": 0.0583,
+      "step": 12630
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9311926605504587,
+      "eval_loss": 0.28844115138053894,
+      "eval_runtime": 2.3738,
+      "eval_samples_per_second": 367.343,
+      "eval_steps_per_second": 45.918,
+      "step": 12630
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.132854229387201e-06,
+      "loss": 0.0484,
+      "step": 14735
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9380733944954128,
+      "eval_loss": 0.32522284984588623,
+      "eval_runtime": 2.2471,
+      "eval_samples_per_second": 388.052,
+      "eval_steps_per_second": 48.506,
+      "step": 14735
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.088569486258134e-06,
+      "loss": 0.0385,
+      "step": 16840
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9334862385321101,
+      "eval_loss": 0.38597530126571655,
+      "eval_runtime": 2.1627,
+      "eval_samples_per_second": 403.202,
+      "eval_steps_per_second": 50.4,
+      "step": 16840
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.044284743129067e-06,
+      "loss": 0.0308,
+      "step": 18945
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9288990825688074,
+      "eval_loss": 0.4163713753223419,
+      "eval_runtime": 2.2597,
+      "eval_samples_per_second": 385.896,
+      "eval_steps_per_second": 48.237,
+      "step": 18945
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0245,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.926605504587156,
+      "eval_loss": 0.4771242141723633,
+      "eval_runtime": 2.1728,
+      "eval_samples_per_second": 401.329,
+      "eval_steps_per_second": 50.166,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "step": 21050,
+      "total_flos": 3.033885148659456e+16,
+      "train_loss": 0.08915798015096126,
+      "train_runtime": 3440.211,
+      "train_samples_per_second": 195.77,
+      "train_steps_per_second": 6.119
+    }
+  ],
+  "max_steps": 21050,
+  "num_train_epochs": 10,
+  "total_flos": 3.033885148659456e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe5fd2624d9443ad09307374aca7ad7ee56c2ee4b863bd1fb82b5820f1bfd1c
+size 2671