added model

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "results/xlnet-base-cased-FalseTrue0-1",
+  "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",
+  "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,
+  "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": "4.6.0.dev0",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4682ac012ec703c13c395cdf2d903fa675cb4248c0f796058ae9ae869f850290
+size 938609441

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ce3a3f9a24b74a093e7f0141c3a97221e3b6f3604ef5a8938e3e3bf2c19a4c
+size 469322193

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1825773cc31372f9e7539e27c6acf17ff906d240466d81932ff305dd2ad4661
+size 623

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>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

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": "results/xlnet-base-cased-FalseTrue0-1"}

trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8004291653633118,
+      "eval_f1": 0.8318264014466547,
+      "eval_loss": 0.6778749227523804,
+      "eval_runtime": 10.0381,
+      "eval_samples_per_second": 46.423,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8025751113891602,
+      "eval_f1": 0.8486842105263158,
+      "eval_loss": 0.46581605076789856,
+      "eval_runtime": 10.1348,
+      "eval_samples_per_second": 45.98,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8133047223091125,
+      "eval_f1": 0.8580750407830342,
+      "eval_loss": 0.42553967237472534,
+      "eval_runtime": 10.1921,
+      "eval_samples_per_second": 45.722,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8412017226219177,
+      "eval_f1": 0.8774834437086093,
+      "eval_loss": 0.38268426060676575,
+      "eval_runtime": 10.2307,
+      "eval_samples_per_second": 45.549,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8798283338546753,
+      "eval_f1": 0.903114186851211,
+      "eval_loss": 0.3336368203163147,
+      "eval_runtime": 10.2564,
+      "eval_samples_per_second": 45.435,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8927038908004761,
+      "eval_f1": 0.9131944444444444,
+      "eval_loss": 0.3360987901687622,
+      "eval_runtime": 10.2682,
+      "eval_samples_per_second": 45.383,
+      "step": 18
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9034335017204285,
+      "eval_f1": 0.9222797927461139,
+      "eval_loss": 0.3484722375869751,
+      "eval_runtime": 10.234,
+      "eval_samples_per_second": 45.535,
+      "step": 21
+    }
+  ],
+  "max_steps": 27,
+  "num_train_epochs": 9,
+  "total_flos": 7838216096256.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8929fa397b0dcda9ce8e2da1b2738c6467b4c882c7b679572a5117fedaec6d1a
+size 2415