Upload 14 files

.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

@@ -1,3 +1,50 @@
 ---
-license: mit
+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
+
+More information needed
+
+## 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
+
+
+
+### 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": 31.943738349432298,
+    "eval_f1": 48.167417022889126,
+    "eval_runtime": 23.4135,
+    "eval_samples": 7265,
+    "eval_samples_per_second": 310.292,
+    "eval_steps_per_second": 38.824,
+    "train_loss": 2.476441317384348,
+    "train_runtime": 1350.7246,
+    "train_samples": 76319,
+    "train_samples_per_second": 113.005,
+    "train_steps_per_second": 9.417
+}

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_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9aa1fd76a6282e88d8f63a0a5f37d330d9ede60b0d4d9b79da2b89905236241
+size 27325361

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 31.943738349432298,
+    "eval_f1": 48.167417022889126,
+    "eval_runtime": 23.4135,
+    "eval_samples": 7265,
+    "eval_samples_per_second": 310.292,
+    "eval_steps_per_second": 38.824
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23580ad9639635b1262d5201009b66d32948f7a9790f97e3a9b88d0b2cdccfa
+size 57039945

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": 2.476441317384348,
+    "train_runtime": 1350.7246,
+    "train_samples": 76319,
+    "train_samples_per_second": 113.005,
+    "train_steps_per_second": 9.417
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 12720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.8820754716981133e-05,
+      "loss": 4.2232,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.7641509433962264e-05,
+      "loss": 3.7067,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.6462264150943396e-05,
+      "loss": 3.4887,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.528301886792453e-05,
+      "loss": 3.1573,
+      "step": 2000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.410377358490566e-05,
+      "loss": 2.8885,
+      "step": 2500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.2924528301886795e-05,
+      "loss": 2.6938,
+      "step": 3000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1745283018867927e-05,
+      "loss": 2.5456,
+      "step": 3500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.0566037735849055e-05,
+      "loss": 2.4776,
+      "step": 4000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.938679245283019e-05,
+      "loss": 2.4,
+      "step": 4500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.8207547169811322e-05,
+      "loss": 2.3852,
+      "step": 5000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.7028301886792454e-05,
+      "loss": 2.349,
+      "step": 5500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5849056603773586e-05,
+      "loss": 2.3696,
+      "step": 6000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.4669811320754717e-05,
+      "loss": 2.2272,
+      "step": 6500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.349056603773585e-05,
+      "loss": 2.1793,
+      "step": 7000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.2311320754716983e-05,
+      "loss": 2.1843,
+      "step": 7500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.1132075471698113e-05,
+      "loss": 2.1425,
+      "step": 8000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 9.952830188679245e-06,
+      "loss": 2.1018,
+      "step": 8500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.773584905660376e-06,
+      "loss": 2.0905,
+      "step": 9000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.59433962264151e-06,
+      "loss": 2.1037,
+      "step": 9500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.415094339622642e-06,
+      "loss": 2.1123,
+      "step": 10000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 5.2358490566037735e-06,
+      "loss": 2.0574,
+      "step": 10500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.056603773584905e-06,
+      "loss": 2.0611,
+      "step": 11000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2.877358490566038e-06,
+      "loss": 2.0564,
+      "step": 11500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.69811320754717e-06,
+      "loss": 2.0539,
+      "step": 12000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.188679245283019e-07,
+      "loss": 2.0636,
+      "step": 12500
+    },
+    {
+      "epoch": 2.0,
+      "step": 12720,
+      "total_flos": 1607163317148672.0,
+      "train_loss": 2.476441317384348,
+      "train_runtime": 1350.7246,
+      "train_samples_per_second": 113.005,
+      "train_steps_per_second": 9.417
+    }
+  ],
+  "max_steps": 12720,
+  "num_train_epochs": 2,
+  "total_flos": 1607163317148672.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915f204152c68aa95cef3f559cc8e85d88158a27aec06664e7da12917adf7469
+size 3515