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 +1,50 @@
+---
+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": 57.961359093937375,
+    "eval_f1": 69.83838750966581,
+    "eval_runtime": 31.6716,
+    "eval_samples": 10720,
+    "eval_samples_per_second": 338.474,
+    "eval_steps_per_second": 42.309,
+    "train_loss": 2.0058399489209733,
+    "train_runtime": 1473.1873,
+    "train_samples": 87504,
+    "train_samples_per_second": 118.795,
+    "train_steps_per_second": 9.9
+}

checkpoint-1000/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
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b17b14ad6fcd0a1156e4dc7b5edad92db5183ba0c70add762133bbd81b6e0c
+size 114064901

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98838f455e90fc23867a8f1287208c5874137cba848ee11a35ecf736f447969
+size 57039945

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c5deaaa4906a6cc3a121941ffd0a024396a5630d7af8fc4515c1dd2841ff10
+size 14575

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eebeab0fa4ccd3d153f3bd0aaf1a39d99e01fb58d321b00ee59cb8efc88cbce
+size 627

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/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]"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.13713658804168952,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.897147558968733e-05,
+      "loss": 3.8538,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.794295117937466e-05,
+      "loss": 2.9886,
+      "step": 1000
+    }
+  ],
+  "max_steps": 14584,
+  "num_train_epochs": 2,
+  "total_flos": 126350972928000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638513e6003a59d7c8294792ee138fe01a9c813ddc5ee1d39599ab0a9f30de31
+size 3515

checkpoint-10000/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
+}

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f747b6d7b55c33b45209b88854bca2706886645300e9c69d7e7d4b0d84d4ca0c
+size 114064901

checkpoint-10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9933636ed2d6c245d145b818df9e101c394b8a6a4bbd85540d8ac21c02919706
+size 57039945

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c1d63ba2e6b207368c62e35db1ae1165ee79da44844bee54e8af97da9ad81c
+size 14575

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04c166fbacbf860bdded5c4cb3abebce049905ce59f2fd58c7cff7b647b71bd
+size 627

checkpoint-10000/special_tokens_map.json

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

checkpoint-10000/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]"
+}

checkpoint-10000/trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3713658804168953,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.897147558968733e-05,
+      "loss": 3.8538,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.794295117937466e-05,
+      "loss": 2.9886,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6914426769061988e-05,
+      "loss": 2.685,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5885902358749317e-05,
+      "loss": 2.4911,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.4857377948436646e-05,
+      "loss": 2.2862,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3828853538123975e-05,
+      "loss": 2.14,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.28003291278113e-05,
+      "loss": 2.122,
+      "step": 3500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.177180471749863e-05,
+      "loss": 2.0886,
+      "step": 4000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.074328030718596e-05,
+      "loss": 2.0471,
+      "step": 4500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9714755896873284e-05,
+      "loss": 1.9984,
+      "step": 5000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8686231486560613e-05,
+      "loss": 2.0018,
+      "step": 5500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7657707076247942e-05,
+      "loss": 1.9633,
+      "step": 6000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.662918266593527e-05,
+      "loss": 1.9129,
+      "step": 6500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.56006582556226e-05,
+      "loss": 1.9094,
+      "step": 7000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.4572133845309929e-05,
+      "loss": 1.8448,
+      "step": 7500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.3543609434997258e-05,
+      "loss": 1.7691,
+      "step": 8000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2515085024684585e-05,
+      "loss": 1.7561,
+      "step": 8500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1486560614371914e-05,
+      "loss": 1.7437,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.0458036204059243e-05,
+      "loss": 1.7462,
+      "step": 9500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.429511793746572e-06,
+      "loss": 1.6874,
+      "step": 10000
+    }
+  ],
+  "max_steps": 14584,
+  "num_train_epochs": 2,
+  "total_flos": 1263509729280000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638513e6003a59d7c8294792ee138fe01a9c813ddc5ee1d39599ab0a9f30de31
+size 3515

checkpoint-10500/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
+}

checkpoint-10500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709602ebef638c9fd45bdc68f1b1ee9cc81ad6855740f15502d021ea5c0484a8
+size 114064901

checkpoint-10500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88173188429c5cded8cdb7cb3347490024fac652e1d88ec13d8c075d37d63956
+size 57039945

checkpoint-10500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543d2c8cbe83fa156b68ee82f62e12bf631397d86f4602ca14d395fe88a56003
+size 14575

checkpoint-10500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220ae99ddf52f42dc878a63cceff78edced869bc7ef25684146225ac65189135
+size 627

checkpoint-10500/special_tokens_map.json

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

checkpoint-10500/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]"
+}

checkpoint-10500/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4399341744377399,
+  "global_step": 10500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.897147558968733e-05,
+      "loss": 3.8538,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.794295117937466e-05,
+      "loss": 2.9886,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6914426769061988e-05,
+      "loss": 2.685,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5885902358749317e-05,
+      "loss": 2.4911,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.4857377948436646e-05,
+      "loss": 2.2862,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3828853538123975e-05,
+      "loss": 2.14,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.28003291278113e-05,
+      "loss": 2.122,
+      "step": 3500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.177180471749863e-05,
+      "loss": 2.0886,
+      "step": 4000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.074328030718596e-05,
+      "loss": 2.0471,
+      "step": 4500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9714755896873284e-05,
+      "loss": 1.9984,
+      "step": 5000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8686231486560613e-05,
+      "loss": 2.0018,
+      "step": 5500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7657707076247942e-05,
+      "loss": 1.9633,
+      "step": 6000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.662918266593527e-05,
+      "loss": 1.9129,
+      "step": 6500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.56006582556226e-05,
+      "loss": 1.9094,
+      "step": 7000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.4572133845309929e-05,
+      "loss": 1.8448,
+      "step": 7500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.3543609434997258e-05,
+      "loss": 1.7691,
+      "step": 8000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2515085024684585e-05,
+      "loss": 1.7561,
+      "step": 8500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1486560614371914e-05,
+      "loss": 1.7437,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.0458036204059243e-05,
+      "loss": 1.7462,
+      "step": 9500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.429511793746572e-06,
+      "loss": 1.6874,
+      "step": 10000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 8.400987383433901e-06,
+      "loss": 1.7223,
+      "step": 10500
+    }
+  ],
+  "max_steps": 14584,
+  "num_train_epochs": 2,
+  "total_flos": 1326685215744000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638513e6003a59d7c8294792ee138fe01a9c813ddc5ee1d39599ab0a9f30de31
+size 3515

checkpoint-11000/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
+}

checkpoint-11000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf61a3f31c943d3368bcaca03973504df92e2abeb6c563985d8fb16a8d3bbc6
+size 114064901

checkpoint-11000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff78f2b6ea9c91e89e16000b02fc76279cdd6cb1e3b0c6216337bf335989351
+size 57039945

checkpoint-11000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ca4efb7c6a220af89ed080062ff5c4773409690397157ccd6a42156396f4a8
+size 14575

checkpoint-11000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b38a031160638f7af2dd9144f8ae33ee78212a1d34243d1d4ddb076da336f3
+size 627

checkpoint-11000/special_tokens_map.json

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

checkpoint-11000/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]"
+}

checkpoint-11000/trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5085024684585848,
+  "global_step": 11000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.897147558968733e-05,
+      "loss": 3.8538,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.794295117937466e-05,
+      "loss": 2.9886,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6914426769061988e-05,
+      "loss": 2.685,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5885902358749317e-05,
+      "loss": 2.4911,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.4857377948436646e-05,
+      "loss": 2.2862,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3828853538123975e-05,
+      "loss": 2.14,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.28003291278113e-05,
+      "loss": 2.122,
+      "step": 3500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.177180471749863e-05,
+      "loss": 2.0886,
+      "step": 4000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.074328030718596e-05,
+      "loss": 2.0471,
+      "step": 4500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9714755896873284e-05,
+      "loss": 1.9984,
+      "step": 5000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8686231486560613e-05,
+      "loss": 2.0018,
+      "step": 5500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7657707076247942e-05,
+      "loss": 1.9633,
+      "step": 6000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.662918266593527e-05,
+      "loss": 1.9129,
+      "step": 6500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.56006582556226e-05,
+      "loss": 1.9094,
+      "step": 7000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.4572133845309929e-05,
+      "loss": 1.8448,
+      "step": 7500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.3543609434997258e-05,
+      "loss": 1.7691,
+      "step": 8000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2515085024684585e-05,
+      "loss": 1.7561,
+      "step": 8500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1486560614371914e-05,
+      "loss": 1.7437,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.0458036204059243e-05,
+      "loss": 1.7462,
+      "step": 9500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.429511793746572e-06,
+      "loss": 1.6874,
+      "step": 10000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 8.400987383433901e-06,
+      "loss": 1.7223,
+      "step": 10500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.372462973121229e-06,
+      "loss": 1.7071,
+      "step": 11000
+    }
+  ],
+  "max_steps": 14584,
+  "num_train_epochs": 2,
+  "total_flos": 1389860702208000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-11000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638513e6003a59d7c8294792ee138fe01a9c813ddc5ee1d39599ab0a9f30de31
+size 3515

checkpoint-11500/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
+}

checkpoint-11500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc20867de0204705f87fbe3650685ccb9185cb3d5a43e48ce4381ccefc11d744
+size 114064901

checkpoint-11500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739f0a30165cdad9d253faefec79d07b0badffb955f3f9f6293e4ce6bffe1fe5
+size 57039945