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:f034a0d7a2afcb0381e29459cb698f80ad638f7ff654302e1e424e1a2c1534c1
+size 938605315

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fd0931c638ac26a3e9ac0e2e736fa962b6055e1157a20a27ed46b4ac6be8cd2
+size 469320127

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2247af90555150bb5cca8425a990ed0c634fafbc2f7309633c20c0dfc65d828
+size 14583

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da584eeca4e93237eda185eba37a8ef8560cb49ee416332f7d9b483f66cf09d0
+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 +1,124 @@
+{
+  "best_metric": 0.9592657342657342,
+  "best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/FalseTrue-0/train_from_dev_and_test.csv/0/checkpoint-81",
+  "epoch": 9.0,
+  "global_step": 81,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8583691120147705,
+      "eval_f1": 0.8558168316831684,
+      "eval_f1_binary": 0.8750000000000001,
+      "eval_f1_weighted": 0.8600157226023032,
+      "eval_loss": 0.336619108915329,
+      "eval_runtime": 1.8593,
+      "eval_samples_per_second": 250.638,
+      "eval_steps_per_second": 31.733,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8712446093559265,
+      "eval_f1": 0.8563619924379419,
+      "eval_f1_binary": 0.9025974025974026,
+      "eval_f1_weighted": 0.8664821895114718,
+      "eval_loss": 0.28895148634910583,
+      "eval_runtime": 1.8336,
+      "eval_samples_per_second": 254.149,
+      "eval_steps_per_second": 32.178,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.946351945400238,
+      "eval_f1": 0.9442250149611011,
+      "eval_f1_binary": 0.9551166965888689,
+      "eval_f1_weighted": 0.946609031111385,
+      "eval_loss": 0.17678162455558777,
+      "eval_runtime": 1.8406,
+      "eval_samples_per_second": 253.179,
+      "eval_steps_per_second": 32.055,
+      "step": 27
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9484978318214417,
+      "eval_f1": 0.9456876456876457,
+      "eval_f1_binary": 0.9580419580419581,
+      "eval_f1_weighted": 0.9483918084776456,
+      "eval_loss": 0.18410657346248627,
+      "eval_runtime": 1.8296,
+      "eval_samples_per_second": 254.697,
+      "eval_steps_per_second": 32.247,
+      "step": 36
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9399141669273376,
+      "eval_f1": 0.9357975122028027,
+      "eval_f1_binary": 0.952054794520548,
+      "eval_f1_weighted": 0.9393559731393049,
+      "eval_loss": 0.23064567148685455,
+      "eval_runtime": 1.9476,
+      "eval_samples_per_second": 239.272,
+      "eval_steps_per_second": 30.294,
+      "step": 45
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.959227442741394,
+      "eval_f1": 0.9571332432811903,
+      "eval_f1_binary": 0.9666080843585237,
+      "eval_f1_weighted": 0.9592071355341688,
+      "eval_loss": 0.1858169287443161,
+      "eval_runtime": 1.8406,
+      "eval_samples_per_second": 253.182,
+      "eval_steps_per_second": 32.055,
+      "step": 54
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9570815563201904,
+      "eval_f1": 0.9550097511054471,
+      "eval_f1_binary": 0.9646643109540636,
+      "eval_f1_weighted": 0.9571229809435562,
+      "eval_loss": 0.19335472583770752,
+      "eval_runtime": 1.8323,
+      "eval_samples_per_second": 254.327,
+      "eval_steps_per_second": 32.2,
+      "step": 63
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.954935610294342,
+      "eval_f1": 0.9527143581938102,
+      "eval_f1_binary": 0.962962962962963,
+      "eval_f1_weighted": 0.9549576150316936,
+      "eval_loss": 0.20666901767253876,
+      "eval_runtime": 1.8259,
+      "eval_samples_per_second": 255.216,
+      "eval_steps_per_second": 32.313,
+      "step": 72
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9613733887672424,
+      "eval_f1": 0.9592657342657342,
+      "eval_f1_binary": 0.9685314685314687,
+      "eval_f1_weighted": 0.9612938563582343,
+      "eval_loss": 0.21665425598621368,
+      "eval_runtime": 1.8426,
+      "eval_samples_per_second": 252.897,
+      "eval_steps_per_second": 32.019,
+      "step": 81
+    }
+  ],
+  "max_steps": 81,
+  "num_train_epochs": 9,
+  "total_flos": 180756537375744.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb57ac574ac406b46809874551bbde8679496b9e8df617fb82b3a50227fbff73
+size 2799