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:ae3219a473e3b96b63070fc7f0a9d8a44d5348402abda9203e1ef16ad60f5a6e
+size 938605244

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f4c8b5d8703e7d12cce21f6c676cba042057aa9b36632ebd41870be9a43214
+size 469320127

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0655a8f37cde43be460274ecae711d7e8c58d41c02a1f4a477e989fb245bc0a
+size 14583

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4368ad420157f7355673704fa0c7355bbd997a50e22ca62121062e961a3b08f8
+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 +1,112 @@
+{
+  "best_metric": 0.7817807192807192,
+  "best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/TrueFalse-0/train_from_dev_and_test.csv/0/checkpoint-72",
+  "epoch": 8.0,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7317596673965454,
+      "eval_f1": 0.6922337227303228,
+      "eval_f1_binary": 0.8025276461295419,
+      "eval_f1_weighted": 0.7163753111138428,
+      "eval_loss": 0.5622926354408264,
+      "eval_runtime": 1.8244,
+      "eval_samples_per_second": 255.432,
+      "eval_steps_per_second": 32.34,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7103004455566406,
+      "eval_f1": 0.6222324972527637,
+      "eval_f1_binary": 0.804630969609262,
+      "eval_f1_weighted": 0.6621566263951731,
+      "eval_loss": 0.5607165694236755,
+      "eval_runtime": 1.8304,
+      "eval_samples_per_second": 254.587,
+      "eval_steps_per_second": 32.233,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7618025541305542,
+      "eval_f1": 0.7149061647421942,
+      "eval_f1_binary": 0.8305343511450382,
+      "eval_f1_weighted": 0.740215338590027,
+      "eval_loss": 0.5542925000190735,
+      "eval_runtime": 1.821,
+      "eval_samples_per_second": 255.897,
+      "eval_steps_per_second": 32.399,
+      "step": 27
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7618025541305542,
+      "eval_f1": 0.7346772332076633,
+      "eval_f1_binary": 0.8195121951219512,
+      "eval_f1_weighted": 0.7532462592060696,
+      "eval_loss": 0.5325024724006653,
+      "eval_runtime": 1.8314,
+      "eval_samples_per_second": 254.445,
+      "eval_steps_per_second": 32.215,
+      "step": 36
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.770386278629303,
+      "eval_f1": 0.7204214256477541,
+      "eval_f1_binary": 0.8386123680241327,
+      "eval_f1_weighted": 0.7462915460820687,
+      "eval_loss": 0.6570885181427002,
+      "eval_runtime": 1.8193,
+      "eval_samples_per_second": 256.143,
+      "eval_steps_per_second": 32.43,
+      "step": 45
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7918455004692078,
+      "eval_f1": 0.759455072772264,
+      "eval_f1_binary": 0.847723704866562,
+      "eval_f1_weighted": 0.7787756746469816,
+      "eval_loss": 0.619213342666626,
+      "eval_runtime": 1.8279,
+      "eval_samples_per_second": 254.931,
+      "eval_steps_per_second": 32.277,
+      "step": 54
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8004291653633118,
+      "eval_f1": 0.7741342019543973,
+      "eval_f1_binary": 0.8511999999999998,
+      "eval_f1_weighted": 0.7910026813549369,
+      "eval_loss": 0.6259479522705078,
+      "eval_runtime": 1.8288,
+      "eval_samples_per_second": 254.808,
+      "eval_steps_per_second": 32.261,
+      "step": 63
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8068669438362122,
+      "eval_f1": 0.7817807192807192,
+      "eval_f1_binary": 0.8557692307692308,
+      "eval_f1_weighted": 0.7979756295206938,
+      "eval_loss": 0.6622598767280579,
+      "eval_runtime": 1.8334,
+      "eval_samples_per_second": 254.179,
+      "eval_steps_per_second": 32.182,
+      "step": 72
+    }
+  ],
+  "max_steps": 81,
+  "num_train_epochs": 9,
+  "total_flos": 160672477667328.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97fdea2904f61695073d9fb39277bb65b922a1b6e161c17eccfcf9223a9f95b0
+size 2799