Upload with huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 result/eval_nbest_predictions.json 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": 32.6889,
+    "eval_samples": 10720,
+    "eval_samples_per_second": 327.941,
+    "eval_steps_per_second": 40.993,
+    "train_loss": 2.0058399489209733,
+    "train_runtime": 1498.6781,
+    "train_samples": 87504,
+    "train_samples_per_second": 116.775,
+    "train_steps_per_second": 9.731
+}

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:b340e18029cb77123da75d23e30cd0b00f2ec5989d7d6aab271a9f535f939be1
+size 49496744

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 57.961359093937375,
+    "eval_f1": 69.83838750966581,
+    "eval_runtime": 32.6889,
+    "eval_samples": 10720,
+    "eval_samples_per_second": 327.941,
+    "eval_steps_per_second": 40.993
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a08a867a30664552d81e9512cf3303906a17ae0428b0602bef4c0a3181ecc0
+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": 2.0058399489209733,
+    "train_runtime": 1498.6781,
+    "train_samples": 87504,
+    "train_samples_per_second": 116.775,
+    "train_steps_per_second": 9.731
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 14584,
+  "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
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 6.343938562808558e-06,
+      "loss": 1.7036,
+      "step": 11500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 5.315414152495887e-06,
+      "loss": 1.6991,
+      "step": 12000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.286889742183214e-06,
+      "loss": 1.6523,
+      "step": 12500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.258365331870543e-06,
+      "loss": 1.6678,
+      "step": 13000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.229840921557872e-06,
+      "loss": 1.6783,
+      "step": 13500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.2013165112452003e-06,
+      "loss": 1.6777,
+      "step": 14000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.727921009325288e-07,
+      "loss": 1.6829,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "step": 14584,
+      "total_flos": 1842702589181952.0,
+      "train_loss": 2.0058399489209733,
+      "train_runtime": 1498.6781,
+      "train_samples_per_second": 116.775,
+      "train_steps_per_second": 9.731
+    }
+  ],
+  "max_steps": 14584,
+  "num_train_epochs": 2,
+  "total_flos": 1842702589181952.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66acec82094efd39d458a8fe525abc7cbca6c8dbd3bc287b3b4a2f983e6fff3
+size 3515