Add model and its dependencies

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "xlnet-base-cased",
+  "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",
+  "finetuning_task": "mnli",
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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
+    }
+  },
+  "transformers_version": "4.9.0.dev0",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6780dc83f3ac3fa331b439691c3f0b9b349b639335ff8307e7ed6f5bee5989b7
+size 469319901

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>"]}

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": "xlnet-base-cased", "tokenizer_class": "XLNetTokenizer"}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.8692817116658176,
+  "best_model_checkpoint": "./outputs/xlnet-base-cased/fine_tuned_models/checkpoint-61360",
+  "epoch": 5.0,
+  "global_step": 61360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.7388593694651082e-05,
+      "loss": 0.5389,
+      "step": 12272
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8557310239429444,
+      "eval_loss": 0.38328248262405396,
+      "eval_runtime": 36.0916,
+      "eval_samples_per_second": 271.947,
+      "eval_steps_per_second": 33.997,
+      "step": 12272
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3041445270988312e-05,
+      "loss": 0.3481,
+      "step": 24544
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8628629648497198,
+      "eval_loss": 0.38958263397216797,
+      "eval_runtime": 36.2238,
+      "eval_samples_per_second": 270.955,
+      "eval_steps_per_second": 33.873,
+      "step": 24544
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.694296847325541e-06,
+      "loss": 0.2489,
+      "step": 36816
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8630667345899133,
+      "eval_loss": 0.3986847400665283,
+      "eval_runtime": 36.0981,
+      "eval_samples_per_second": 271.898,
+      "eval_steps_per_second": 33.991,
+      "step": 36816
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.3471484236627705e-06,
+      "loss": 0.1777,
+      "step": 49088
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8691798267957208,
+      "eval_loss": 0.46929463744163513,
+      "eval_runtime": 36.2027,
+      "eval_samples_per_second": 271.112,
+      "eval_steps_per_second": 33.892,
+      "step": 49088
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.1303,
+      "step": 61360
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8692817116658176,
+      "eval_loss": 0.5496333837509155,
+      "eval_runtime": 36.1007,
+      "eval_samples_per_second": 271.879,
+      "eval_steps_per_second": 33.988,
+      "step": 61360
+    },
+    {
+      "epoch": 5.0,
+      "step": 61360,
+      "total_flos": 1.769024893707648e+17,
+      "train_loss": 0.28879537967846014,
+      "train_runtime": 20254.0743,
+      "train_samples_per_second": 96.944,
+      "train_steps_per_second": 3.03
+    }
+  ],
+  "max_steps": 61360,
+  "num_train_epochs": 5,
+  "total_flos": 1.769024893707648e+17,
+  "trial_name": null,
+  "trial_params": null
+}