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
+model-index:
+- name: wd_0.01_bs_12_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_12_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 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: 36
+- 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 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 80.56764427625355,
+    "eval_f1": 88.20408506306627,
+    "eval_runtime": 64.6352,
+    "eval_samples": 10822,
+    "eval_samples_per_second": 167.432,
+    "eval_steps_per_second": 6.978,
+    "train_loss": 0.8512596145846539,
+    "train_runtime": 3575.2739,
+    "train_samples": 88729,
+    "train_samples_per_second": 99.27,
+    "train_steps_per_second": 2.758
+}

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 sha256:79226e833cb294b468823a615696e7accdd3669e91c2daefb35f06249f06b4d4
+size 48649013

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 80.56764427625355,
+    "eval_f1": 88.20408506306627,
+    "eval_runtime": 64.6352,
+    "eval_samples": 10822,
+    "eval_samples_per_second": 167.432,
+    "eval_steps_per_second": 6.978
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36218bf33ad0523c586a275648e1574b0e23a488464826971992624eb39f3bd
+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": 0.8512596145846539,
+    "train_runtime": 3575.2739,
+    "train_samples": 88729,
+    "train_samples_per_second": 99.27,
+    "train_steps_per_second": 2.758
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 9860,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8985801217038542e-05,
+      "loss": 2.0844,
+      "step": 500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.797160243407708e-05,
+      "loss": 1.322,
+      "step": 1000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6957403651115622e-05,
+      "loss": 1.1934,
+      "step": 1500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.594320486815416e-05,
+      "loss": 1.1366,
+      "step": 2000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.4929006085192699e-05,
+      "loss": 1.0634,
+      "step": 2500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3914807302231239e-05,
+      "loss": 0.855,
+      "step": 3000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.2900608519269777e-05,
+      "loss": 0.8663,
+      "step": 3500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.1886409736308317e-05,
+      "loss": 0.8364,
+      "step": 4000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.0872210953346858e-05,
+      "loss": 0.835,
+      "step": 4500
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.858012170385396e-06,
+      "loss": 0.8107,
+      "step": 5000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 8.843813387423936e-06,
+      "loss": 0.6625,
+      "step": 5500
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 7.829614604462476e-06,
+      "loss": 0.6576,
+      "step": 6000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.815415821501015e-06,
+      "loss": 0.6617,
+      "step": 6500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.801217038539554e-06,
+      "loss": 0.6515,
+      "step": 7000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.787018255578094e-06,
+      "loss": 0.6179,
+      "step": 7500
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.7728194726166332e-06,
+      "loss": 0.5304,
+      "step": 8000
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.7586206896551725e-06,
+      "loss": 0.5401,
+      "step": 8500
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.7444219066937122e-06,
+      "loss": 0.5549,
+      "step": 9000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 7.302231237322515e-07,
+      "loss": 0.5237,
+      "step": 9500
+    },
+    {
+      "epoch": 4.0,
+      "step": 9860,
+      "total_flos": 6.955379978528563e+16,
+      "train_loss": 0.8512596145846539,
+      "train_runtime": 3575.2739,
+      "train_samples_per_second": 99.27,
+      "train_steps_per_second": 2.758
+    }
+  ],
+  "max_steps": 9860,
+  "num_train_epochs": 4,
+  "total_flos": 6.955379978528563e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779e8af9b73cbb07cfe8d904c2e7d5e2283cd0362a3bdf03cfbbc6ee392b9c88
+size 3707