Upload 12 files

README.md

@@ -1,3 +1,59 @@
 ---
-license: openrail
+tags:
+- generated_from_trainer
+model-index:
+- name: result
+  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. -->
+
+# result
+
+This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+NewsQA from https://github.com/mrqa/MRQA-Shared-Task-2019
+
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-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: 2.0
+
+### Training results
+***** eval metrics *****
+  epoch                   =        2.0
+  eval_exact_match        =     0.6648
+  eval_f1                 =     4.3787
+  eval_runtime            = 0:00:31.81
+  eval_samples            =      10567
+  eval_samples_per_second =    332.115
+  eval_steps_per_second   =     41.518
+
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.13.1+cu116
+- Datasets 2.9.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 0.6647673314339981,
+    "eval_f1": 4.378741273434903,
+    "eval_runtime": 31.8173,
+    "eval_samples": 10567,
+    "eval_samples_per_second": 332.115,
+    "eval_steps_per_second": 41.518,
+    "train_loss": 1.6433022868307863,
+    "train_runtime": 3179.4331,
+    "train_samples": 187263,
+    "train_samples_per_second": 117.796,
+    "train_steps_per_second": 9.817
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "structure": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 0.6647673314339981,
+    "eval_f1": 4.378741273434903,
+    "eval_runtime": 31.8173,
+    "eval_samples": 10567,
+    "eval_samples_per_second": 332.115,
+    "eval_steps_per_second": 41.518
+}

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
+  "never_split": null,
+  "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": 2.0,
+    "train_loss": 1.6433022868307863,
+    "train_runtime": 3179.4331,
+    "train_samples": 187263,
+    "train_samples_per_second": 117.796,
+    "train_steps_per_second": 9.817
+}

trainer_state.json

@@ -0,0 +1,397 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 31212,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.9519415609381006e-05,
+      "loss": 2.3707,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.9038831218762015e-05,
+      "loss": 1.8657,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.8558246828143025e-05,
+      "loss": 1.8001,
+      "step": 1500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.807766243752403e-05,
+      "loss": 1.8241,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.759707804690504e-05,
+      "loss": 1.8568,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.7116493656286045e-05,
+      "loss": 1.7976,
+      "step": 3000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.663590926566705e-05,
+      "loss": 1.7969,
+      "step": 3500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.6155324875048056e-05,
+      "loss": 1.772,
+      "step": 4000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.567474048442907e-05,
+      "loss": 1.7746,
+      "step": 4500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.5194156093810074e-05,
+      "loss": 1.7575,
+      "step": 5000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.471357170319108e-05,
+      "loss": 1.7777,
+      "step": 5500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.423298731257209e-05,
+      "loss": 1.7731,
+      "step": 6000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.3752402921953095e-05,
+      "loss": 1.7775,
+      "step": 6500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.32718185313341e-05,
+      "loss": 1.7627,
+      "step": 7000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.2791234140715113e-05,
+      "loss": 1.7435,
+      "step": 7500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.231064975009612e-05,
+      "loss": 1.7182,
+      "step": 8000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1830065359477124e-05,
+      "loss": 1.7493,
+      "step": 8500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.1349480968858133e-05,
+      "loss": 1.715,
+      "step": 9000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.086889657823914e-05,
+      "loss": 1.7109,
+      "step": 9500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.0388312187620145e-05,
+      "loss": 1.651,
+      "step": 10000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.9907727797001154e-05,
+      "loss": 1.7383,
+      "step": 10500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.9427143406382163e-05,
+      "loss": 1.6754,
+      "step": 11000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.8946559015763168e-05,
+      "loss": 1.5948,
+      "step": 11500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.8465974625144174e-05,
+      "loss": 1.6431,
+      "step": 12000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7985390234525183e-05,
+      "loss": 1.6536,
+      "step": 12500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7504805843906192e-05,
+      "loss": 1.5941,
+      "step": 13000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.7024221453287198e-05,
+      "loss": 1.6606,
+      "step": 13500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6543637062668207e-05,
+      "loss": 1.6621,
+      "step": 14000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6063052672049212e-05,
+      "loss": 1.622,
+      "step": 14500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5582468281430218e-05,
+      "loss": 1.6216,
+      "step": 15000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5101883890811225e-05,
+      "loss": 1.618,
+      "step": 15500
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.4621299500192235e-05,
+      "loss": 1.5934,
+      "step": 16000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.414071510957324e-05,
+      "loss": 1.602,
+      "step": 16500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.366013071895425e-05,
+      "loss": 1.5458,
+      "step": 17000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.3179546328335255e-05,
+      "loss": 1.5039,
+      "step": 17500
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.2698961937716264e-05,
+      "loss": 1.5694,
+      "step": 18000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.2218377547097271e-05,
+      "loss": 1.5937,
+      "step": 18500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1737793156478277e-05,
+      "loss": 1.5364,
+      "step": 19000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.1257208765859286e-05,
+      "loss": 1.5487,
+      "step": 19500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.0776624375240293e-05,
+      "loss": 1.5565,
+      "step": 20000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.0296039984621299e-05,
+      "loss": 1.5503,
+      "step": 20500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 9.815455594002308e-06,
+      "loss": 1.577,
+      "step": 21000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 9.334871203383314e-06,
+      "loss": 1.5346,
+      "step": 21500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 8.854286812764321e-06,
+      "loss": 1.5686,
+      "step": 22000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 8.37370242214533e-06,
+      "loss": 1.5372,
+      "step": 22500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 7.893118031526336e-06,
+      "loss": 1.5534,
+      "step": 23000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.412533640907344e-06,
+      "loss": 1.5061,
+      "step": 23500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.9319492502883506e-06,
+      "loss": 1.5766,
+      "step": 24000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.451364859669358e-06,
+      "loss": 1.5215,
+      "step": 24500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.970780469050365e-06,
+      "loss": 1.5602,
+      "step": 25000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.490196078431373e-06,
+      "loss": 1.5311,
+      "step": 25500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 5.00961168781238e-06,
+      "loss": 1.5018,
+      "step": 26000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.529027297193387e-06,
+      "loss": 1.5673,
+      "step": 26500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.048442906574395e-06,
+      "loss": 1.5459,
+      "step": 27000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.5678585159554016e-06,
+      "loss": 1.5127,
+      "step": 27500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.0872741253364094e-06,
+      "loss": 1.4852,
+      "step": 28000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 2.6066897347174164e-06,
+      "loss": 1.5609,
+      "step": 28500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.1261053440984237e-06,
+      "loss": 1.4866,
+      "step": 29000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.645520953479431e-06,
+      "loss": 1.5449,
+      "step": 29500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.1649365628604384e-06,
+      "loss": 1.4855,
+      "step": 30000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.843521722414456e-07,
+      "loss": 1.5881,
+      "step": 30500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2.037677816224529e-07,
+      "loss": 1.5224,
+      "step": 31000
+    },
+    {
+      "epoch": 2.0,
+      "step": 31212,
+      "total_flos": 3943477040569344.0,
+      "train_loss": 1.6433022868307863,
+      "train_runtime": 3179.4331,
+      "train_samples_per_second": 117.796,
+      "train_steps_per_second": 9.817
+    }
+  ],
+  "max_steps": 31212,
+  "num_train_epochs": 2,
+  "total_flos": 3943477040569344.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f6f0801f0a956245416f3c234f8d21eeab500c17d16001b5c22aa9021d74d2
+size 3451