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_0.02_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_0.02_bs_12_lr_2e-05_epochs_4
+
+This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-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: 12
+- eval_batch_size: 8
+- 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 1.12.1
+- Datasets 2.11.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 76.72658467360453,
+    "eval_f1": 85.0827668289791,
+    "eval_runtime": 246.6613,
+    "eval_samples": 10822,
+    "eval_samples_per_second": 43.874,
+    "eval_steps_per_second": 5.485,
+    "train_loss": 0.9484633781685871,
+    "train_runtime": 41623.2409,
+    "train_samples": 88729,
+    "train_samples_per_second": 8.527,
+    "train_steps_per_second": 0.711
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForQuestionAnswering"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "vocab_size": 28996
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f43a5163f0254f665e391fb95c69b86269ce680001e22ae29d7c6254f3b94992
+size 48852170

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_exact_match": 76.72658467360453,
+    "eval_f1": 85.0827668289791,
+    "eval_runtime": 246.6613,
+    "eval_samples": 10822,
+    "eval_samples_per_second": 43.874,
+    "eval_steps_per_second": 5.485
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c45178d407acc07ebefd8ec5c203e365dab479bcf551b791ccd9db22fc9def
+size 260802037

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.9484633781685871,
+    "train_runtime": 41623.2409,
+    "train_samples": 88729,
+    "train_samples_per_second": 8.527,
+    "train_steps_per_second": 0.711
+}

trainer_state.json

@@ -0,0 +1,379 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 29580,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9661933739012847e-05,
+      "loss": 3.2523,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9323867478025696e-05,
+      "loss": 2.1296,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8985801217038542e-05,
+      "loss": 1.8245,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8647734956051387e-05,
+      "loss": 1.5861,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8309668695064233e-05,
+      "loss": 1.5392,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.797160243407708e-05,
+      "loss": 1.4796,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7633536173089927e-05,
+      "loss": 1.3667,
+      "step": 3500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7295469912102773e-05,
+      "loss": 1.3543,
+      "step": 4000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6957403651115622e-05,
+      "loss": 1.3346,
+      "step": 4500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.6619337390128468e-05,
+      "loss": 1.33,
+      "step": 5000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6281271129141313e-05,
+      "loss": 1.3025,
+      "step": 5500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.594320486815416e-05,
+      "loss": 1.255,
+      "step": 6000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.5605138607167004e-05,
+      "loss": 1.2358,
+      "step": 6500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5267072346179853e-05,
+      "loss": 1.1977,
+      "step": 7000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.4929006085192699e-05,
+      "loss": 1.1565,
+      "step": 7500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4590939824205546e-05,
+      "loss": 0.9745,
+      "step": 8000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4252873563218392e-05,
+      "loss": 0.9552,
+      "step": 8500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3914807302231239e-05,
+      "loss": 0.9697,
+      "step": 9000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3576741041244086e-05,
+      "loss": 0.9713,
+      "step": 9500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.323867478025693e-05,
+      "loss": 0.9844,
+      "step": 10000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.2900608519269777e-05,
+      "loss": 0.9559,
+      "step": 10500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.2562542258282625e-05,
+      "loss": 0.9701,
+      "step": 11000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.222447599729547e-05,
+      "loss": 0.9309,
+      "step": 11500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.1886409736308317e-05,
+      "loss": 0.9617,
+      "step": 12000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1548343475321165e-05,
+      "loss": 0.957,
+      "step": 12500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.121027721433401e-05,
+      "loss": 0.952,
+      "step": 13000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.0872210953346858e-05,
+      "loss": 0.9282,
+      "step": 13500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.0534144692359703e-05,
+      "loss": 0.9389,
+      "step": 14000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.0196078431372549e-05,
+      "loss": 0.9239,
+      "step": 14500
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.858012170385396e-06,
+      "loss": 0.8506,
+      "step": 15000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.519945909398243e-06,
+      "loss": 0.6999,
+      "step": 15500
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.181879648411089e-06,
+      "loss": 0.7386,
+      "step": 16000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 8.843813387423936e-06,
+      "loss": 0.7238,
+      "step": 16500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.505747126436782e-06,
+      "loss": 0.7343,
+      "step": 17000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.167680865449629e-06,
+      "loss": 0.7243,
+      "step": 17500
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 7.829614604462476e-06,
+      "loss": 0.7298,
+      "step": 18000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.491548343475323e-06,
+      "loss": 0.7104,
+      "step": 18500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.153482082488168e-06,
+      "loss": 0.7206,
+      "step": 19000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.815415821501015e-06,
+      "loss": 0.7174,
+      "step": 19500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.477349560513861e-06,
+      "loss": 0.6925,
+      "step": 20000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.139283299526708e-06,
+      "loss": 0.7066,
+      "step": 20500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.801217038539554e-06,
+      "loss": 0.7251,
+      "step": 21000
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.4631507775524e-06,
+      "loss": 0.7088,
+      "step": 21500
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.1250845165652475e-06,
+      "loss": 0.7033,
+      "step": 22000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.787018255578094e-06,
+      "loss": 0.5892,
+      "step": 22500
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.44895199459094e-06,
+      "loss": 0.5616,
+      "step": 23000
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 4.110885733603787e-06,
+      "loss": 0.5337,
+      "step": 23500
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.7728194726166332e-06,
+      "loss": 0.5533,
+      "step": 24000
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 3.4347532116294797e-06,
+      "loss": 0.5603,
+      "step": 24500
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 3.0966869506423265e-06,
+      "loss": 0.5499,
+      "step": 25000
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.7586206896551725e-06,
+      "loss": 0.573,
+      "step": 25500
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 2.420554428668019e-06,
+      "loss": 0.5759,
+      "step": 26000
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 2.0824881676808658e-06,
+      "loss": 0.5804,
+      "step": 26500
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.7444219066937122e-06,
+      "loss": 0.5794,
+      "step": 27000
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 1.4063556457065586e-06,
+      "loss": 0.5502,
+      "step": 27500
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.068289384719405e-06,
+      "loss": 0.558,
+      "step": 28000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 7.302231237322515e-07,
+      "loss": 0.5506,
+      "step": 28500
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 0.5485,
+      "step": 29000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 5.409060175794456e-08,
+      "loss": 0.5576,
+      "step": 29500
+    },
+    {
+      "epoch": 4.0,
+      "step": 29580,
+      "total_flos": 3.4778156738217984e+16,
+      "train_loss": 0.9484633781685871,
+      "train_runtime": 41623.2409,
+      "train_samples_per_second": 8.527,
+      "train_steps_per_second": 0.711
+    }
+  ],
+  "max_steps": 29580,
+  "num_train_epochs": 4,
+  "total_flos": 3.4778156738217984e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f82b40fc70336da788df30cad7f3dbdf392b0f95b49bd13f3e4bb0b0a925d1
+size 3695