Upload 11 files

README.md

@@ -0,0 +1,51 @@
+---
+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 [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-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": 2.0,
+    "eval_exact_match": 50.68632435180478,
+    "eval_f1": 68.16490105690133,
+    "eval_runtime": 22.9046,
+    "eval_samples": 7265,
+    "eval_samples_per_second": 317.185,
+    "eval_steps_per_second": 39.686,
+    "train_loss": 1.7758963099065816,
+    "train_runtime": 1367.5464,
+    "train_samples": 76319,
+    "train_samples_per_second": 111.614,
+    "train_steps_per_second": 9.301
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "microsoft/xtremedistil-l6-h256-uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "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_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 50.68632435180478,
+    "eval_f1": 68.16490105690133,
+    "eval_runtime": 22.9046,
+    "eval_samples": 7265,
+    "eval_samples_per_second": 317.185,
+    "eval_steps_per_second": 39.686
+}

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/xtremedistil-l6-h256-uncased",
+  "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": 1.7758963099065816,
+    "train_runtime": 1367.5464,
+    "train_samples": 76319,
+    "train_samples_per_second": 111.614,
+    "train_steps_per_second": 9.301
+}

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": 4.3332,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.7641509433962264e-05,
+      "loss": 3.1388,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.6462264150943396e-05,
+      "loss": 2.557,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.528301886792453e-05,
+      "loss": 2.2015,
+      "step": 2000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.410377358490566e-05,
+      "loss": 1.9948,
+      "step": 2500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.2924528301886795e-05,
+      "loss": 1.9278,
+      "step": 3000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1745283018867927e-05,
+      "loss": 1.8199,
+      "step": 3500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.0566037735849055e-05,
+      "loss": 1.7275,
+      "step": 4000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.938679245283019e-05,
+      "loss": 1.6389,
+      "step": 4500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.8207547169811322e-05,
+      "loss": 1.636,
+      "step": 5000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.7028301886792454e-05,
+      "loss": 1.6225,
+      "step": 5500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5849056603773586e-05,
+      "loss": 1.5949,
+      "step": 6000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.4669811320754717e-05,
+      "loss": 1.4982,
+      "step": 6500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.349056603773585e-05,
+      "loss": 1.475,
+      "step": 7000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.2311320754716983e-05,
+      "loss": 1.4551,
+      "step": 7500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.1132075471698113e-05,
+      "loss": 1.4413,
+      "step": 8000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 9.952830188679245e-06,
+      "loss": 1.4178,
+      "step": 8500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.773584905660376e-06,
+      "loss": 1.3974,
+      "step": 9000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.59433962264151e-06,
+      "loss": 1.4176,
+      "step": 9500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.415094339622642e-06,
+      "loss": 1.4098,
+      "step": 10000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 5.2358490566037735e-06,
+      "loss": 1.3751,
+      "step": 10500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.056603773584905e-06,
+      "loss": 1.3756,
+      "step": 11000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2.877358490566038e-06,
+      "loss": 1.3999,
+      "step": 11500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.69811320754717e-06,
+      "loss": 1.3809,
+      "step": 12000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.188679245283019e-07,
+      "loss": 1.3565,
+      "step": 12500
+    },
+    {
+      "epoch": 2.0,
+      "step": 12720,
+      "total_flos": 1666807897807872.0,
+      "train_loss": 1.7758963099065816,
+      "train_runtime": 1367.5464,
+      "train_samples_per_second": 111.614,
+      "train_steps_per_second": 9.301
+    }
+  ],
+  "max_steps": 12720,
+  "num_train_epochs": 2,
+  "total_flos": 1666807897807872.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480fc227d1ab992229872db5943d13cc2e7ec03cbb5f6a56fe9bdc27748bef2a
+size 3515