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:cb7e0de244e72df12595f299e6666309d446fd0ae070f76c6a0b70971199f58e
+size 938605237

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496f1d803d020752b7c68d5d32f97a18af45fd89b70183af9aaa38db6ae054f9
+size 469320114

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75dee9924250c1927fc1079e5280a05c7e5004209c8b016edf9ac167cb9bd15d
+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": 0.7920443179195198,
+  "best_model_checkpoint": "output-no-git/EN-OUTPUT/ON_FS_OUT/XLNetFalseTrue-0-1/FalseFalse-0/train_from_dev_and_test.csv/4/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": 0.7725321650505066,
+      "eval_f1": 0.7563771232417289,
+      "eval_f1_binary": 0.8191126279863481,
+      "eval_f1_weighted": 0.7701089290012807,
+      "eval_loss": 0.5054362416267395,
+      "eval_runtime": 1.8375,
+      "eval_samples_per_second": 253.611,
+      "eval_steps_per_second": 32.11,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.721030056476593,
+      "eval_f1": 0.6446920821114369,
+      "eval_f1_binary": 0.8093841642228738,
+      "eval_f1_weighted": 0.6807405636036398,
+      "eval_loss": 0.6385602355003357,
+      "eval_runtime": 1.8316,
+      "eval_samples_per_second": 254.426,
+      "eval_steps_per_second": 32.213,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7811158895492554,
+      "eval_f1": 0.7456549657534247,
+      "eval_f1_binary": 0.8406250000000001,
+      "eval_f1_weighted": 0.7664423981421601,
+      "eval_loss": 0.6955846548080444,
+      "eval_runtime": 1.8305,
+      "eval_samples_per_second": 254.578,
+      "eval_steps_per_second": 32.232,
+      "step": 27
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7854077219963074,
+      "eval_f1": 0.760603320729903,
+      "eval_f1_binary": 0.8376623376623377,
+      "eval_f1_weighted": 0.7774703158524531,
+      "eval_loss": 0.7326841354370117,
+      "eval_runtime": 1.8306,
+      "eval_samples_per_second": 254.558,
+      "eval_steps_per_second": 32.229,
+      "step": 36
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7875536680221558,
+      "eval_f1": 0.7535932317454214,
+      "eval_f1_binary": 0.8450704225352113,
+      "eval_f1_weighted": 0.7736161361672208,
+      "eval_loss": 0.9596889019012451,
+      "eval_runtime": 1.8322,
+      "eval_samples_per_second": 254.333,
+      "eval_steps_per_second": 32.201,
+      "step": 45
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8111587762832642,
+      "eval_f1": 0.7893309222423146,
+      "eval_f1_binary": 0.8571428571428571,
+      "eval_f1_weighted": 0.8041738779501587,
+      "eval_loss": 0.8485983610153198,
+      "eval_runtime": 1.8435,
+      "eval_samples_per_second": 252.776,
+      "eval_steps_per_second": 32.004,
+      "step": 54
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8025751113891602,
+      "eval_f1": 0.7738818565400843,
+      "eval_f1_binary": 0.8544303797468354,
+      "eval_f1_weighted": 0.7915126491733218,
+      "eval_loss": 1.0803866386413574,
+      "eval_runtime": 1.8504,
+      "eval_samples_per_second": 251.841,
+      "eval_steps_per_second": 31.885,
+      "step": 63
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8133047223091125,
+      "eval_f1": 0.7907477277067516,
+      "eval_f1_binary": 0.8594507269789984,
+      "eval_f1_weighted": 0.8057857232556125,
+      "eval_loss": 0.9846170544624329,
+      "eval_runtime": 1.8389,
+      "eval_samples_per_second": 253.41,
+      "eval_steps_per_second": 32.084,
+      "step": 72
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8133047223091125,
+      "eval_f1": 0.7920443179195198,
+      "eval_f1_binary": 0.8585365853658536,
+      "eval_f1_weighted": 0.8065984193777302,
+      "eval_loss": 0.9904114007949829,
+      "eval_runtime": 1.8392,
+      "eval_samples_per_second": 253.365,
+      "eval_steps_per_second": 32.078,
+      "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 sha256:6fcda02e4d25f3872f20e3770d4031d38de44646330301b39fe8dda4b45427ec
+size 2799