initial upload

.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: 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-h384-uncased](https://huggingface.co/microsoft/xtremedistil-l6-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+cu117
+- Datasets 2.9.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 61.51449049548146,
+    "eval_f1": 74.00787001955999,
+    "eval_runtime": 76.2744,
+    "eval_samples": 19278,
+    "eval_samples_per_second": 252.745,
+    "eval_steps_per_second": 31.596,
+    "train_loss": 1.375746032769238,
+    "train_runtime": 3467.9128,
+    "train_samples": 148108,
+    "train_samples_per_second": 85.416,
+    "train_steps_per_second": 7.118
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "microsoft/xtremedistil-l6-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": 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_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a571d969fca41622d8458041356c1127f782cebc4009b29f281b82d2979f332e
+size 60587117

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 61.51449049548146,
+    "eval_f1": 74.00787001955999,
+    "eval_runtime": 76.2744,
+    "eval_samples": 19278,
+    "eval_samples_per_second": 252.745,
+    "eval_steps_per_second": 31.596
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7eb94973941c147733f2f76a97ef63ef13fd7ba2aff232dff89e3bb41e0d75
+size 90303789

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-h384-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": 1.375746032769238,
+    "train_runtime": 3467.9128,
+    "train_samples": 148108,
+    "train_samples_per_second": 85.416,
+    "train_steps_per_second": 7.118
+}

trainer_state.json

@@ -0,0 +1,319 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "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": 3.3491,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.8784736287774447e-05,
+      "loss": 2.2763,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.817710443166167e-05,
+      "loss": 1.9944,
+      "step": 1500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.7569472575548894e-05,
+      "loss": 1.8569,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.6961840719436117e-05,
+      "loss": 1.7046,
+      "step": 2500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.6354208863323343e-05,
+      "loss": 1.7023,
+      "step": 3000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.5746577007210563e-05,
+      "loss": 1.6104,
+      "step": 3500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.513894515109779e-05,
+      "loss": 1.5678,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.4531313294985013e-05,
+      "loss": 1.5883,
+      "step": 4500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3923681438872236e-05,
+      "loss": 1.5575,
+      "step": 5000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.331604958275946e-05,
+      "loss": 1.5272,
+      "step": 5500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.2708417726646683e-05,
+      "loss": 1.5003,
+      "step": 6000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2100785870533906e-05,
+      "loss": 1.469,
+      "step": 6500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.1493154014421133e-05,
+      "loss": 1.4697,
+      "step": 7000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.0885522158308352e-05,
+      "loss": 1.4479,
+      "step": 7500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.027789030219558e-05,
+      "loss": 1.4523,
+      "step": 8000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.96702584460828e-05,
+      "loss": 1.4069,
+      "step": 8500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.9062626589970022e-05,
+      "loss": 1.4024,
+      "step": 9000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.845499473385725e-05,
+      "loss": 1.4032,
+      "step": 9500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.784736287774447e-05,
+      "loss": 1.4305,
+      "step": 10000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7239731021631695e-05,
+      "loss": 1.4093,
+      "step": 10500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.663209916551892e-05,
+      "loss": 1.399,
+      "step": 11000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.602446730940614e-05,
+      "loss": 1.3776,
+      "step": 11500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5416835453293365e-05,
+      "loss": 1.39,
+      "step": 12000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.4809203597180588e-05,
+      "loss": 1.3543,
+      "step": 12500
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.4201571741067811e-05,
+      "loss": 1.2738,
+      "step": 13000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.3593939884955035e-05,
+      "loss": 1.2945,
+      "step": 13500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.298630802884226e-05,
+      "loss": 1.2711,
+      "step": 14000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.2378676172729483e-05,
+      "loss": 1.2579,
+      "step": 14500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1771044316616706e-05,
+      "loss": 1.2537,
+      "step": 15000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.1163412460503929e-05,
+      "loss": 1.2593,
+      "step": 15500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.0555780604391152e-05,
+      "loss": 1.2928,
+      "step": 16000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 9.948148748278377e-06,
+      "loss": 1.2569,
+      "step": 16500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 9.3405168921656e-06,
+      "loss": 1.2638,
+      "step": 17000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.732885036052824e-06,
+      "loss": 1.2703,
+      "step": 17500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.125253179940047e-06,
+      "loss": 1.2729,
+      "step": 18000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.517621323827271e-06,
+      "loss": 1.2209,
+      "step": 18500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.909989467714494e-06,
+      "loss": 1.2705,
+      "step": 19000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 6.3023576116017175e-06,
+      "loss": 1.2463,
+      "step": 19500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 5.6947257554889415e-06,
+      "loss": 1.2464,
+      "step": 20000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 5.087093899376165e-06,
+      "loss": 1.2421,
+      "step": 20500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.479462043263389e-06,
+      "loss": 1.2716,
+      "step": 21000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.871830187150612e-06,
+      "loss": 1.2582,
+      "step": 21500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.2641983310378353e-06,
+      "loss": 1.25,
+      "step": 22000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2.656566474925059e-06,
+      "loss": 1.2221,
+      "step": 22500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.0489346188122826e-06,
+      "loss": 1.22,
+      "step": 23000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.4413027626995058e-06,
+      "loss": 1.2384,
+      "step": 23500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 8.336709065867294e-07,
+      "loss": 1.2515,
+      "step": 24000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.2603905047395284e-07,
+      "loss": 1.2498,
+      "step": 24500
+    },
+    {
+      "epoch": 2.0,
+      "step": 24686,
+      "total_flos": 7267284517367808.0,
+      "train_loss": 1.375746032769238,
+      "train_runtime": 3467.9128,
+      "train_samples_per_second": 85.416,
+      "train_steps_per_second": 7.118
+    }
+  ],
+  "max_steps": 24686,
+  "num_train_epochs": 2,
+  "total_flos": 7267284517367808.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18332d702a71ffac1b776688af94a2ee7a5802768d7098c371be3b6c8407ddaa
+size 3515