Upload model and auxiliary 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

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 76.80499325236167,
+    "eval_f1": 85.78998205229026,
+    "eval_runtime": 32.987,
+    "eval_samples": 6056,
+    "eval_samples_per_second": 183.587,
+    "eval_steps_per_second": 22.948,
+    "train_loss": 1.3483753287818292,
+    "train_runtime": 2670.4215,
+    "train_samples": 87739,
+    "train_samples_per_second": 65.712,
+    "train_steps_per_second": 5.476
+}

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": "4.38.0.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:c2b6387515c64ad85b175de8109231a5c65d26a4878f0cb12b90b41089eb5eb6
+size 27739432

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 76.80499325236167,
+    "eval_f1": 85.78998205229026,
+    "eval_runtime": 32.987,
+    "eval_samples": 6056,
+    "eval_samples_per_second": 183.587,
+    "eval_steps_per_second": 22.948
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b049ac2723d75fd5784b479c798dc51b3665b232eb27decb96aedf65bfd797b
+size 90276408

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": 1.3483753287818292,
+    "train_runtime": 2670.4215,
+    "train_samples": 87739,
+    "train_samples_per_second": 65.712,
+    "train_steps_per_second": 5.476
+}

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": 3.4331,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.7948577680525165e-05,
+      "loss": 2.1219,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6922866520787748e-05,
+      "loss": 1.8112,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.589715536105033e-05,
+      "loss": 1.6588,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.4871444201312912e-05,
+      "loss": 1.5237,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3845733041575492e-05,
+      "loss": 1.463,
+      "step": 3000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.2820021881838072e-05,
+      "loss": 1.4293,
+      "step": 3500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.179431072210066e-05,
+      "loss": 1.3813,
+      "step": 4000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.076859956236324e-05,
+      "loss": 1.3349,
+      "step": 4500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.9742888402625823e-05,
+      "loss": 1.2893,
+      "step": 5000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8717177242888403e-05,
+      "loss": 1.3047,
+      "step": 5500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7691466083150983e-05,
+      "loss": 1.2601,
+      "step": 6000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6665754923413567e-05,
+      "loss": 1.2731,
+      "step": 6500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.564004376367615e-05,
+      "loss": 1.2453,
+      "step": 7000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.4614332603938733e-05,
+      "loss": 1.2107,
+      "step": 7500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.3588621444201313e-05,
+      "loss": 1.1359,
+      "step": 8000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.2562910284463895e-05,
+      "loss": 1.1168,
+      "step": 8500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.1537199124726478e-05,
+      "loss": 1.1197,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.0511487964989058e-05,
+      "loss": 1.1077,
+      "step": 9500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.485776805251642e-06,
+      "loss": 1.1104,
+      "step": 10000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 8.460065645514224e-06,
+      "loss": 1.1168,
+      "step": 10500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.434354485776806e-06,
+      "loss": 1.1007,
+      "step": 11000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.408643326039388e-06,
+      "loss": 1.066,
+      "step": 11500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 5.3829321663019695e-06,
+      "loss": 1.1172,
+      "step": 12000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.357221006564551e-06,
+      "loss": 1.1203,
+      "step": 12500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.3315098468271337e-06,
+      "loss": 1.0972,
+      "step": 13000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.3057986870897156e-06,
+      "loss": 1.0766,
+      "step": 13500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.2800875273522977e-06,
+      "loss": 1.0916,
+      "step": 14000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.543763676148797e-07,
+      "loss": 1.0628,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "step": 14624,
+      "total_flos": 4305130555198464.0,
+      "train_loss": 1.3483753287818292,
+      "train_runtime": 2670.4215,
+      "train_samples_per_second": 65.712,
+      "train_steps_per_second": 5.476
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 4305130555198464.0,
+  "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:bdce91777575d68d947a37ab9ddd61f085907d54dba6a98c4df9e028a4d09453
+size 4728