Upload with huggingface_hub

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: wd_0.01_bs_24_lr_1e-05_epochs_4
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wd_0.01_bs_24_lr_1e-05_epochs_4
+
+This model is a fine-tuned version of [xlnet-large-cased](https://huggingface.co/xlnet-large-cased) on the squad dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 72
+- eval_batch_size: 192
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.4
+- Pytorch 1.13.1
+- Datasets 2.11.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 86.87795648060549,
+    "eval_f1": 93.4076288561567,
+    "eval_runtime": 182.8274,
+    "eval_samples": 10848,
+    "eval_samples_per_second": 59.335,
+    "eval_steps_per_second": 0.312,
+    "train_loss": 0.6981605795639261,
+    "train_runtime": 13226.0556,
+    "train_samples": 88835,
+    "train_samples_per_second": 26.867,
+    "train_steps_per_second": 0.373
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "xlnet-large-cased",
+  "architectures": [
+    "XLNetForQuestionAnswering"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 4096,
+  "d_model": 1024,
+  "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": 16,
+  "n_layer": 24,
+  "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": "4.27.4",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1208a9d6ddf4a47ee7b6a07d8b7070587946757939ca3b52e0297192160c1e
+size 40116595

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 86.87795648060549,
+    "eval_f1": 93.4076288561567,
+    "eval_runtime": 182.8274,
+    "eval_samples": 10848,
+    "eval_samples_per_second": 59.335,
+    "eval_steps_per_second": 0.312
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea56f235f809af3eb6c1727540f5da60919cbd47cffdb38c02f72b5aedb9bae9
+size 1458021793

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.6981605795639261,
+    "train_runtime": 13226.0556,
+    "train_samples": 88835,
+    "train_samples_per_second": 26.867,
+    "train_steps_per_second": 0.373
+}

trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 4936,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.987034035656403e-06,
+      "loss": 1.5994,
+      "step": 500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 7.974068071312805e-06,
+      "loss": 0.8358,
+      "step": 1000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.961102106969206e-06,
+      "loss": 0.7185,
+      "step": 1500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 5.948136142625608e-06,
+      "loss": 0.6419,
+      "step": 2000
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 4.93517017828201e-06,
+      "loss": 0.6228,
+      "step": 2500
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 3.922204213938412e-06,
+      "loss": 0.5474,
+      "step": 3000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.9092382495948142e-06,
+      "loss": 0.5291,
+      "step": 3500
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.8962722852512159e-06,
+      "loss": 0.5007,
+      "step": 4000
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 8.833063209076175e-07,
+      "loss": 0.4824,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "step": 4936,
+      "total_flos": 2.7156576624344064e+17,
+      "train_loss": 0.6981605795639261,
+      "train_runtime": 13226.0556,
+      "train_samples_per_second": 26.867,
+      "train_steps_per_second": 0.373
+    }
+  ],
+  "max_steps": 4936,
+  "num_train_epochs": 4,
+  "total_flos": 2.7156576624344064e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f2d6c5ccc801f95eb761862b4d626f500f11a01281e6702b9150fa5df29b63
+size 3643