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

@@ -0,0 +1,51 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) 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": 1.83,
+    "eval_exact_match": 67.13929573075724,
+    "eval_f1": 79.12211169002747,
+    "eval_runtime": 180.1273,
+    "eval_samples": 19278,
+    "eval_samples_per_second": 107.024,
+    "eval_steps_per_second": 13.379,
+    "train_loss": 0.4519888086604075,
+    "train_runtime": 3497.3077,
+    "train_samples": 148108,
+    "train_samples_per_second": 84.698,
+    "train_steps_per_second": 7.059
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "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 sha256:9c6d00c9bf4ab53db0e1b7c66033a1282c692a14cc498f01177cbddb54204d7f
+size 59010378

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.83,
+    "eval_exact_match": 67.13929573075724,
+    "eval_f1": 79.12211169002747,
+    "eval_runtime": 180.1273,
+    "eval_samples": 19278,
+    "eval_samples_per_second": 107.024,
+    "eval_steps_per_second": 13.379
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ceb5a336ceadedb590eedba2ad211f60ed67e21fd04cdca4f50ca492654ef1
+size 132923885

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": "microsoft/MiniLM-L12-H384-uncased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--microsoft--MiniLM-L12-H384-uncased/snapshots/44acabbec0ef496f6dbc93adadea57f376b7c0ec/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.83,
+    "train_loss": 0.4519888086604075,
+    "train_runtime": 3497.3077,
+    "train_samples": 148108,
+    "train_samples_per_second": 84.698,
+    "train_steps_per_second": 7.059
+}

trainer_state.json

@@ -0,0 +1,319 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8252450781819656,
+  "global_step": 24686,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9392368143887224e-05,
+      "loss": 2.6222,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.8784736287774447e-05,
+      "loss": 1.7824,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.817710443166167e-05,
+      "loss": 1.6134,
+      "step": 1500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.7569472575548894e-05,
+      "loss": 1.492,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.6961840719436117e-05,
+      "loss": 1.4179,
+      "step": 2500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.6354208863323343e-05,
+      "loss": 1.4101,
+      "step": 3000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.5746577007210563e-05,
+      "loss": 1.3602,
+      "step": 3500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.513894515109779e-05,
+      "loss": 1.3182,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.4531313294985013e-05,
+      "loss": 1.3338,
+      "step": 4500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3923681438872236e-05,
+      "loss": 1.3377,
+      "step": 5000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.331604958275946e-05,
+      "loss": 1.3059,
+      "step": 5500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.2708417726646683e-05,
+      "loss": 1.2811,
+      "step": 6000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2100785870533906e-05,
+      "loss": 1.2666,
+      "step": 6500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.1493154014421133e-05,
+      "loss": 1.2554,
+      "step": 7000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.0885522158308352e-05,
+      "loss": 1.2196,
+      "step": 7500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.027789030219558e-05,
+      "loss": 1.2499,
+      "step": 8000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.96702584460828e-05,
+      "loss": 1.197,
+      "step": 8500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.9062626589970022e-05,
+      "loss": 1.2032,
+      "step": 9000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.845499473385725e-05,
+      "loss": 1.2115,
+      "step": 9500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.784736287774447e-05,
+      "loss": 1.2381,
+      "step": 10000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7239731021631695e-05,
+      "loss": 1.2194,
+      "step": 10500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.663209916551892e-05,
+      "loss": 1.2124,
+      "step": 11000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.602446730940614e-05,
+      "loss": 1.1917,
+      "step": 11500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5416835453293365e-05,
+      "loss": 1.1998,
+      "step": 12000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.4809203597180588e-05,
+      "loss": 1.1596,
+      "step": 12500
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.4201571741067811e-05,
+      "loss": 1.0373,
+      "step": 13000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.3593939884955035e-05,
+      "loss": 1.0618,
+      "step": 13500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.298630802884226e-05,
+      "loss": 1.0332,
+      "step": 14000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2378676172729483e-05,
+      "loss": 1.0407,
+      "step": 14500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.9392368143887224e-05,
+      "loss": 1.0722,
+      "step": 15000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.8784736287774447e-05,
+      "loss": 1.0825,
+      "step": 15500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.817710443166167e-05,
+      "loss": 1.1312,
+      "step": 16000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.7569472575548894e-05,
+      "loss": 1.1025,
+      "step": 16500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.6961840719436117e-05,
+      "loss": 1.1045,
+      "step": 17000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 2.6354208863323343e-05,
+      "loss": 1.1177,
+      "step": 17500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.5746577007210563e-05,
+      "loss": 1.1005,
+      "step": 18000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.513894515109779e-05,
+      "loss": 1.0777,
+      "step": 18500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.4531313294985013e-05,
+      "loss": 1.1009,
+      "step": 19000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.3923681438872236e-05,
+      "loss": 1.0944,
+      "step": 19500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.331604958275946e-05,
+      "loss": 1.1001,
+      "step": 20000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.2708417726646683e-05,
+      "loss": 1.0926,
+      "step": 20500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.2100785870533906e-05,
+      "loss": 1.1123,
+      "step": 21000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.1493154014421133e-05,
+      "loss": 1.109,
+      "step": 21500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.0885522158308352e-05,
+      "loss": 1.1017,
+      "step": 22000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.027789030219558e-05,
+      "loss": 1.0779,
+      "step": 22500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.96702584460828e-05,
+      "loss": 1.067,
+      "step": 23000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.9062626589970022e-05,
+      "loss": 1.0914,
+      "step": 23500
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.845499473385725e-05,
+      "loss": 1.0886,
+      "step": 24000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.784736287774447e-05,
+      "loss": 1.0861,
+      "step": 24500
+    },
+    {
+      "epoch": 1.83,
+      "step": 24686,
+      "total_flos": 1.4533519377936384e+16,
+      "train_loss": 0.4519888086604075,
+      "train_runtime": 3497.3077,
+      "train_samples_per_second": 84.698,
+      "train_steps_per_second": 7.059
+    }
+  ],
+  "max_steps": 24686,
+  "num_train_epochs": 2,
+  "total_flos": 1.4533519377936384e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a07368f8e9f3c49ac59ec018d24ac6b252d4e4adfb4d19ac29776412d2525e3
+size 3579