Upload folder using huggingface_hub

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "xlnet-base-cased",
+  "architectures": [
+    "XLNetForQuestionAnsweringSimple"
+  ],
+  "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,
+  "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": "4.34.0",
+  "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 sha256:45f30861522142cc15b202717697f4126824941058894429626cb07f0958d363
+size 933926906

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80412c26de8304ac024da88b8e52be8c4ec65f081b9ce93731dd943fe7a4506b
+size 466949130

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c1253a54b3fcdc548d767d132ea67b73eb6f0ffebeec1b4a7372acd04f32e8
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889e9e9917f17317ce1591c2cd0d22795dded31aa702ed7cda2119c66916ffc6
+size 1064

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,93 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "keep_accents": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.8954964280128479,
+  "best_model_checkpoint": "finetune_xlnet-base-cased/checkpoint-2738",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2738,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.879474068663258e-05,
+      "loss": 1.9283,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7577307036766496e-05,
+      "loss": 1.1706,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.6359873386900417e-05,
+      "loss": 1.0596,
+      "step": 1500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5142439737034334e-05,
+      "loss": 1.0009,
+      "step": 2000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3925006087168251e-05,
+      "loss": 0.9825,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8954964280128479,
+      "eval_runtime": 572.6201,
+      "eval_samples_per_second": 18.459,
+      "eval_steps_per_second": 0.145,
+      "step": 2738
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8214,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.8597222647483904e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4841904c5de2553acafbf7dfbc3b229076133d7743f3aca5cae78f730d303e1
+size 4536