Init

.gitattributes

@@ -32,3 +32,6 @@ 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
+dev_file.json filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
+train_file.json filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 57.478436410350525,
+    "eval_f1": 64.17262260441153,
+    "eval_runtime": 76.5432,
+    "eval_samples": 21803,
+    "eval_samples_per_second": 284.846,
+    "eval_steps_per_second": 35.614,
+    "train_loss": 1.7420501031286595,
+    "train_runtime": 3238.8409,
+    "train_samples": 172919,
+    "train_samples_per_second": 106.778,
+    "train_steps_per_second": 8.898
+}

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
+}

dev_file.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073b0306a7e87c357abb4048b4f2d73c29f05d47bff410c9eb40ac4d6db91a31
+size 25863305

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe31133f05afef046c1b50b0d8cf9d7c77ec934d8d5e3d69b27451d2a9953fb
+size 23671936

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 57.478436410350525,
+    "eval_f1": 64.17262260441153,
+    "eval_runtime": 76.5432,
+    "eval_samples": 21803,
+    "eval_samples_per_second": 284.846,
+    "eval_steps_per_second": 35.614
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e7a4a6c8a42b7fb2193fd5a158de170367c22847a1f4047825a9c082e34d73
+size 50778413

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 +1,15 @@
+{
+  "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]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_file.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12192f9e2d5c0ebef31f2cce4ecd947749e90e9f5e49d2326c115e0b46a448c
+size 205194285

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.7420501031286595,
+    "train_runtime": 3238.8409,
+    "train_samples": 172919,
+    "train_samples_per_second": 106.778,
+    "train_steps_per_second": 8.898
+}

trainer_state.json

@@ -0,0 +1,367 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 28820,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.9479528105482305e-05,
+      "loss": 3.92,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.895905621096461e-05,
+      "loss": 2.8996,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.8438584316446913e-05,
+      "loss": 2.5707,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.7918112421929218e-05,
+      "loss": 2.5034,
+      "step": 2000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.7397640527411522e-05,
+      "loss": 2.4225,
+      "step": 2500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6877168632893823e-05,
+      "loss": 2.38,
+      "step": 3000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.635669673837613e-05,
+      "loss": 2.3628,
+      "step": 3500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.583622484385843e-05,
+      "loss": 2.3135,
+      "step": 4000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.5315752949340735e-05,
+      "loss": 2.3292,
+      "step": 4500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.479528105482304e-05,
+      "loss": 2.3096,
+      "step": 5000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.4274809160305344e-05,
+      "loss": 2.3131,
+      "step": 5500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.3754337265787648e-05,
+      "loss": 2.2757,
+      "step": 6000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.3233865371269952e-05,
+      "loss": 2.2894,
+      "step": 6500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.2713393476752253e-05,
+      "loss": 2.2692,
+      "step": 7000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.219292158223456e-05,
+      "loss": 2.2477,
+      "step": 7500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.1672449687716865e-05,
+      "loss": 2.2531,
+      "step": 8000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.115197779319917e-05,
+      "loss": 2.2083,
+      "step": 8500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.0631505898681473e-05,
+      "loss": 2.2013,
+      "step": 9000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.0111034004163774e-05,
+      "loss": 1.664,
+      "step": 9500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9590562109646082e-05,
+      "loss": 1.5101,
+      "step": 10000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.9070090215128383e-05,
+      "loss": 1.5157,
+      "step": 10500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.8549618320610687e-05,
+      "loss": 1.4644,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.802914642609299e-05,
+      "loss": 1.4997,
+      "step": 11500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7508674531575295e-05,
+      "loss": 1.4426,
+      "step": 12000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.69882026370576e-05,
+      "loss": 1.4494,
+      "step": 12500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6467730742539904e-05,
+      "loss": 1.5178,
+      "step": 13000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5947258848022205e-05,
+      "loss": 1.4849,
+      "step": 13500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5426786953504512e-05,
+      "loss": 1.4418,
+      "step": 14000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.4906315058986815e-05,
+      "loss": 1.4934,
+      "step": 14500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.4385843164469119e-05,
+      "loss": 1.4166,
+      "step": 15000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.3865371269951423e-05,
+      "loss": 1.3893,
+      "step": 15500
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.3344899375433727e-05,
+      "loss": 1.3942,
+      "step": 16000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.282442748091603e-05,
+      "loss": 1.4259,
+      "step": 16500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.2303955586398334e-05,
+      "loss": 1.4207,
+      "step": 17000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.1783483691880638e-05,
+      "loss": 1.388,
+      "step": 17500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.1263011797362943e-05,
+      "loss": 1.3931,
+      "step": 18000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.0742539902845247e-05,
+      "loss": 1.4201,
+      "step": 18500
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.0222068008327551e-05,
+      "loss": 1.4258,
+      "step": 19000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 9.701596113809855e-06,
+      "loss": 1.3959,
+      "step": 19500
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 9.18112421929216e-06,
+      "loss": 1.3601,
+      "step": 20000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.660652324774464e-06,
+      "loss": 1.371,
+      "step": 20500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 8.140180430256766e-06,
+      "loss": 1.4411,
+      "step": 21000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.61970853573907e-06,
+      "loss": 1.4025,
+      "step": 21500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 7.0992366412213746e-06,
+      "loss": 1.3712,
+      "step": 22000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.578764746703678e-06,
+      "loss": 1.3896,
+      "step": 22500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 6.058292852185982e-06,
+      "loss": 1.4191,
+      "step": 23000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.5378209576682855e-06,
+      "loss": 1.3655,
+      "step": 23500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 5.01734906315059e-06,
+      "loss": 1.3739,
+      "step": 24000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.496877168632893e-06,
+      "loss": 1.3649,
+      "step": 24500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.976405274115198e-06,
+      "loss": 1.3496,
+      "step": 25000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.4559333795975016e-06,
+      "loss": 1.4169,
+      "step": 25500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.935461485079806e-06,
+      "loss": 1.3761,
+      "step": 26000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.4149895905621096e-06,
+      "loss": 1.3611,
+      "step": 26500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.8945176960444136e-06,
+      "loss": 1.3619,
+      "step": 27000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.3740458015267176e-06,
+      "loss": 1.4141,
+      "step": 27500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 8.535739070090215e-07,
+      "loss": 1.4094,
+      "step": 28000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 3.3310201249132546e-07,
+      "loss": 1.3732,
+      "step": 28500
+    },
+    {
+      "epoch": 2.0,
+      "step": 28820,
+      "total_flos": 3776553084828672.0,
+      "train_loss": 1.7420501031286595,
+      "train_runtime": 3238.8409,
+      "train_samples_per_second": 106.778,
+      "train_steps_per_second": 8.898
+    }
+  ],
+  "max_steps": 28820,
+  "num_train_epochs": 2,
+  "total_flos": 3776553084828672.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601ae6d8fceec65ae63b411bf5fed8ba9e7802d9bebe728d620c291df97c09e5
+size 3515