added model

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "output-no-git/EN-OUTPUT/xlnet-base-cased/ForZeroFew/",
+  "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,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0.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:bb47c3bb9f58a2ba26180143b62ac5400d67b5dafd721c5e0b9dbe93898baecb
+size 938605239

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78929f895682ab38c929013c843566e7f693399f505bf2d1267a5fa2b0596b6a
+size 469320121

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e28831b676884e78c14d390d08b0b63da3c45cdbb4592180b1e5a4030591cf2
+size 14647

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ed8d437cfafed01dafe48b65bd0fd4caab59bdfea3ce2338ac47f90843b18c
+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": "output-no-git/EN-OUTPUT/xlnet-base-cased/ForZeroFew/", "tokenizer_class": "XLNetTokenizer"}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": 0.688748846434271,
+  "best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/TrueFalse-0/train_from_dev_and_test_short.csv/1/checkpoint-18",
+  "epoch": 6.0,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7060086131095886,
+      "eval_f1": 0.6763806868584463,
+      "eval_f1_binary": 0.7742998352553541,
+      "eval_f1_weighted": 0.697813633503263,
+      "eval_loss": 0.6087642312049866,
+      "eval_runtime": 1.8252,
+      "eval_samples_per_second": 255.31,
+      "eval_steps_per_second": 32.325,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7038626670837402,
+      "eval_f1": 0.6863881086142323,
+      "eval_f1_binary": 0.7604166666666667,
+      "eval_f1_weighted": 0.702591784411117,
+      "eval_loss": 0.5733329057693481,
+      "eval_runtime": 1.8207,
+      "eval_samples_per_second": 255.939,
+      "eval_steps_per_second": 32.404,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7145922780036926,
+      "eval_f1": 0.6748046823760278,
+      "eval_f1_binary": 0.7885532591414944,
+      "eval_f1_weighted": 0.6997024395221171,
+      "eval_loss": 0.5822879672050476,
+      "eval_runtime": 1.8268,
+      "eval_samples_per_second": 255.088,
+      "eval_steps_per_second": 32.297,
+      "step": 9
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6995708346366882,
+      "eval_f1": 0.6317370001580527,
+      "eval_f1_binary": 0.7897897897897898,
+      "eval_f1_weighted": 0.6663322459572741,
+      "eval_loss": 0.652556300163269,
+      "eval_runtime": 1.8238,
+      "eval_samples_per_second": 255.509,
+      "eval_steps_per_second": 32.35,
+      "step": 12
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.725321888923645,
+      "eval_f1": 0.6831548529661737,
+      "eval_f1_binary": 0.7987421383647799,
+      "eval_f1_weighted": 0.7084550742336797,
+      "eval_loss": 0.6597227454185486,
+      "eval_runtime": 1.8184,
+      "eval_samples_per_second": 256.267,
+      "eval_steps_per_second": 32.446,
+      "step": 15
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7188841104507446,
+      "eval_f1": 0.688748846434271,
+      "eval_f1_binary": 0.7855973813420623,
+      "eval_f1_weighted": 0.7099474527874785,
+      "eval_loss": 0.6554996371269226,
+      "eval_runtime": 1.8291,
+      "eval_samples_per_second": 254.774,
+      "eval_steps_per_second": 32.257,
+      "step": 18
+    }
+  ],
+  "max_steps": 27,
+  "num_train_epochs": 9,
+  "total_flos": 37176876481536.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c146e371639d286af83d895091321a5f3482815a9fe7b4654bed3864ea4b0c9
+size 2799