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: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: wd_0.01_bs_24_lr_2e-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_2e-05_epochs_4
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the squad_v2 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: 2e-05
+- train_batch_size: 72
+- eval_batch_size: 24
+- 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 0.11.0

all_results.json

@@ -0,0 +1,25 @@
+{
+    "epoch": 4.0,
+    "eval_HasAns_exact": 71.94669365721997,
+    "eval_HasAns_f1": 78.58199531347474,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 68.24222035323801,
+    "eval_NoAns_f1": 68.24222035323801,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 70.09180493556809,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 73.4047054845681,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 70.09180493556809,
+    "eval_f1": 73.40470548456818,
+    "eval_runtime": 72.5963,
+    "eval_samples": 12199,
+    "eval_samples_per_second": 168.039,
+    "eval_steps_per_second": 7.011,
+    "eval_total": 11873,
+    "train_loss": 0.9501987717132152,
+    "train_runtime": 4143.6655,
+    "train_samples": 132079,
+    "train_samples_per_second": 127.5,
+    "train_steps_per_second": 1.771
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f4991f4b126b664a73a4cc28fd930edebb35e8f4b715f1d2c848759a8f31cf
+size 55762387

eval_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 4.0,
+    "eval_HasAns_exact": 71.94669365721997,
+    "eval_HasAns_f1": 78.58199531347474,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 68.24222035323801,
+    "eval_NoAns_f1": 68.24222035323801,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 70.09180493556809,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 73.4047054845681,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 70.09180493556809,
+    "eval_f1": 73.40470548456818,
+    "eval_runtime": 72.5963,
+    "eval_samples": 12199,
+    "eval_samples_per_second": 168.039,
+    "eval_steps_per_second": 7.011,
+    "eval_total": 11873
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cde3ee3a0398c3ac8452a657112777833deba8bdbf1368d64b65965907a9ef2
+size 430957037

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.9501987717132152,
+    "train_runtime": 4143.6655,
+    "train_samples": 132079,
+    "train_samples_per_second": 127.5,
+    "train_steps_per_second": 1.771
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 7340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8637602179836514e-05,
+      "loss": 2.0167,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7275204359673027e-05,
+      "loss": 1.3794,
+      "step": 1000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.591280653950954e-05,
+      "loss": 1.2342,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.455040871934605e-05,
+      "loss": 1.0997,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.3188010899182562e-05,
+      "loss": 0.9627,
+      "step": 2500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.1825613079019073e-05,
+      "loss": 0.9457,
+      "step": 3000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.0463215258855586e-05,
+      "loss": 0.9263,
+      "step": 3500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.1008174386921e-06,
+      "loss": 0.7995,
+      "step": 4000
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.73841961852861e-06,
+      "loss": 0.7548,
+      "step": 4500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.376021798365123e-06,
+      "loss": 0.7403,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.013623978201635e-06,
+      "loss": 0.7507,
+      "step": 5500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.6512261580381475e-06,
+      "loss": 0.6354,
+      "step": 6000
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 2.2888283378746596e-06,
+      "loss": 0.6395,
+      "step": 6500
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 9.264305177111717e-07,
+      "loss": 0.6381,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "step": 7340,
+      "total_flos": 1.0353544299880243e+17,
+      "train_loss": 0.9501987717132152,
+      "train_runtime": 4143.6655,
+      "train_samples_per_second": 127.5,
+      "train_steps_per_second": 1.771
+    }
+  ],
+  "max_steps": 7340,
+  "num_train_epochs": 4,
+  "total_flos": 1.0353544299880243e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a2b32bb9f053e48cb3b49193e3a5edfc8f92dd7ad71f3879a05a39772a40ddf
+size 3643