Upload 14 files

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,52 @@
+---
+license: mit
+base_model: microsoft/xtremedistil-l12-h384-uncased
+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-l12-h384-uncased](https://huggingface.co/microsoft/xtremedistil-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 4.38.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 82.06815114709852,
+    "eval_f1": 89.82829333158949,
+    "eval_runtime": 59.1307,
+    "eval_samples": 6056,
+    "eval_samples_per_second": 102.417,
+    "eval_steps_per_second": 12.802,
+    "train_loss": 1.091546323158548,
+    "train_runtime": 5151.5391,
+    "train_samples": 87739,
+    "train_samples_per_second": 34.063,
+    "train_steps_per_second": 2.839
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "microsoft/xtremedistil-l12-h384-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": 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": "4.38.0.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 sha256:0e03a35e81d51176814dc2cfeb26df367e62941c51a539835f9c11fa7f4cc6d3
+size 27515838

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 82.06815114709852,
+    "eval_f1": 89.82829333158949,
+    "eval_runtime": 59.1307,
+    "eval_samples": 6056,
+    "eval_samples_per_second": 102.417,
+    "eval_steps_per_second": 12.802
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:034fbf5c19381007f4a60a9618b559da16d611c4ca3bdfa2108265c5ee816b4f
+size 132874824

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "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": 1.091546323158548,
+    "train_runtime": 5151.5391,
+    "train_samples": 87739,
+    "train_samples_per_second": 34.063,
+    "train_steps_per_second": 2.839
+}

trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 14624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.897428884026258e-05,
+      "loss": 3.0501,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.7948577680525165e-05,
+      "loss": 1.7725,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6922866520787748e-05,
+      "loss": 1.4732,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.589715536105033e-05,
+      "loss": 1.3494,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.4871444201312912e-05,
+      "loss": 1.2387,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3845733041575492e-05,
+      "loss": 1.1847,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.2820021881838072e-05,
+      "loss": 1.175,
+      "step": 3500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.179431072210066e-05,
+      "loss": 1.1402,
+      "step": 4000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.076859956236324e-05,
+      "loss": 1.0992,
+      "step": 4500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.9742888402625823e-05,
+      "loss": 1.0572,
+      "step": 5000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8717177242888403e-05,
+      "loss": 1.0772,
+      "step": 5500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7691466083150983e-05,
+      "loss": 1.0323,
+      "step": 6000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6665754923413567e-05,
+      "loss": 1.0316,
+      "step": 6500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.564004376367615e-05,
+      "loss": 1.0258,
+      "step": 7000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.4614332603938733e-05,
+      "loss": 0.9686,
+      "step": 7500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.3588621444201313e-05,
+      "loss": 0.891,
+      "step": 8000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.2562910284463895e-05,
+      "loss": 0.8679,
+      "step": 8500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1537199124726478e-05,
+      "loss": 0.8807,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.0511487964989058e-05,
+      "loss": 0.8578,
+      "step": 9500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.485776805251642e-06,
+      "loss": 0.8673,
+      "step": 10000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 8.460065645514224e-06,
+      "loss": 0.8724,
+      "step": 10500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.434354485776806e-06,
+      "loss": 0.8711,
+      "step": 11000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.408643326039388e-06,
+      "loss": 0.8336,
+      "step": 11500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 5.3829321663019695e-06,
+      "loss": 0.8622,
+      "step": 12000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.357221006564551e-06,
+      "loss": 0.8772,
+      "step": 12500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.3315098468271337e-06,
+      "loss": 0.8538,
+      "step": 13000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.3057986870897156e-06,
+      "loss": 0.8541,
+      "step": 13500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.2800875273522977e-06,
+      "loss": 0.8422,
+      "step": 14000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.543763676148797e-07,
+      "loss": 0.8156,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "step": 14624,
+      "total_flos": 8609639294979072.0,
+      "train_loss": 1.091546323158548,
+      "train_runtime": 5151.5391,
+      "train_samples_per_second": 34.063,
+      "train_steps_per_second": 2.839
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8609639294979072.0,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ebc229a3c2fdea9b20f5965d30eeda31a53f07e99604522482e3828667e597
+size 4728