Add model and its dependencies

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9426605504587156,
+    "eval_loss": 0.18346692621707916,
+    "eval_runtime": 1.9212,
+    "eval_samples": 872,
+    "eval_samples_per_second": 453.884,
+    "eval_steps_per_second": 56.735,
+    "train_loss": 0.08974739491514809,
+    "train_runtime": 3412.6761,
+    "train_samples": 67349,
+    "train_samples_per_second": 197.35,
+    "train_steps_per_second": 6.168
+}

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": 0.9426605504587156,
+    "eval_loss": 0.18346692621707916,
+    "eval_runtime": 1.9212,
+    "eval_samples": 872,
+    "eval_samples_per_second": 453.884,
+    "eval_steps_per_second": 56.735
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e35bc496595a18cdba0a76f55b5aaecccd4caf00e3de18fbb9693c100a3dc3
+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": 0.08974739491514809,
+    "train_runtime": 3412.6761,
+    "train_samples": 67349,
+    "train_samples_per_second": 197.35,
+    "train_steps_per_second": 6.168
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.9426605504587156,
+  "best_model_checkpoint": "./electra-base-discriminator/fine_tuned_models/checkpoint-2105",
+  "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": 0.2722,
+      "step": 2105
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9426605504587156,
+      "eval_loss": 0.18346692621707916,
+      "eval_runtime": 1.9622,
+      "eval_samples_per_second": 444.393,
+      "eval_steps_per_second": 55.549,
+      "step": 2105
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6354277945032536e-05,
+      "loss": 0.147,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9369266055045872,
+      "eval_loss": 0.21615296602249146,
+      "eval_runtime": 2.1784,
+      "eval_samples_per_second": 400.29,
+      "eval_steps_per_second": 50.036,
+      "step": 4210
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.4309993201903469e-05,
+      "loss": 0.1107,
+      "step": 6315
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9380733944954128,
+      "eval_loss": 0.19852299988269806,
+      "eval_runtime": 2.3414,
+      "eval_samples_per_second": 372.432,
+      "eval_steps_per_second": 46.554,
+      "step": 6315
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.2265708458774402e-05,
+      "loss": 0.0895,
+      "step": 8420
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9369266055045872,
+      "eval_loss": 0.22530296444892883,
+      "eval_runtime": 1.8651,
+      "eval_samples_per_second": 467.524,
+      "eval_steps_per_second": 58.441,
+      "step": 8420
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.0221423715645335e-05,
+      "loss": 0.0742,
+      "step": 10525
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.930045871559633,
+      "eval_loss": 0.2544686794281006,
+      "eval_runtime": 1.9656,
+      "eval_samples_per_second": 443.633,
+      "eval_steps_per_second": 55.454,
+      "step": 10525
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 8.177138972516268e-06,
+      "loss": 0.0589,
+      "step": 12630
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9369266055045872,
+      "eval_loss": 0.2618718445301056,
+      "eval_runtime": 2.1931,
+      "eval_samples_per_second": 397.616,
+      "eval_steps_per_second": 49.702,
+      "step": 12630
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 6.132854229387201e-06,
+      "loss": 0.0476,
+      "step": 14735
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9311926605504587,
+      "eval_loss": 0.3039261996746063,
+      "eval_runtime": 2.0002,
+      "eval_samples_per_second": 435.966,
+      "eval_steps_per_second": 54.496,
+      "step": 14735
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.088569486258134e-06,
+      "loss": 0.0397,
+      "step": 16840
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9334862385321101,
+      "eval_loss": 0.30574584007263184,
+      "eval_runtime": 2.0703,
+      "eval_samples_per_second": 421.19,
+      "eval_steps_per_second": 52.649,
+      "step": 16840
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.044284743129067e-06,
+      "loss": 0.0316,
+      "step": 18945
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9380733944954128,
+      "eval_loss": 0.38161835074424744,
+      "eval_runtime": 2.2112,
+      "eval_samples_per_second": 394.362,
+      "eval_steps_per_second": 49.295,
+      "step": 18945
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0261,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9346330275229358,
+      "eval_loss": 0.3954842984676361,
+      "eval_runtime": 2.1873,
+      "eval_samples_per_second": 398.661,
+      "eval_steps_per_second": 49.833,
+      "step": 21050
+    },
+    {
+      "epoch": 10.0,
+      "step": 21050,
+      "total_flos": 3.033885148659456e+16,
+      "train_loss": 0.08974739491514809,
+      "train_runtime": 3412.6761,
+      "train_samples_per_second": 197.35,
+      "train_steps_per_second": 6.168
+    }
+  ],
+  "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:c0749420db12aad96d826ecd62f22ab5483faea06a0d677894455cf7dfb57653
+size 2671