Upload 15 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

@@ -1,3 +1,52 @@
----
-license: apache-2.0
----
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: scibert-lr3-seed42
+  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. -->
+
+# scibert-lr3-seed42
+
+This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the squad_v2 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 4.20.1
+- Pytorch 1.12.0+cu116
+- Datasets 2.3.2
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 2.0,
+    "eval_HasAns_exact": 70.59716599190283,
+    "eval_HasAns_f1": 77.27675544056615,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 80.47098402018503,
+    "eval_NoAns_f1": 80.47098402018503,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 75.54114377158258,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 78.87615651071133,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 75.54114377158258,
+    "eval_f1": 78.8761565107113,
+    "eval_samples": 12246,
+    "eval_total": 11873,
+    "train_loss": 0.9776556768279144,
+    "train_runtime": 8352.3756,
+    "train_samples": 132469,
+    "train_samples_per_second": 31.72,
+    "train_steps_per_second": 2.644
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "allenai/scibert_scivocab_uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.20.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37c336ef126e18b100ddee97f0c2233c51cd30c569ec0b2a5d354c510090906
+size 55652362

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 2.0,
+    "eval_HasAns_exact": 70.59716599190283,
+    "eval_HasAns_f1": 77.27675544056615,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 80.47098402018503,
+    "eval_NoAns_f1": 80.47098402018503,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 75.54114377158258,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 78.87615651071133,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 75.54114377158258,
+    "eval_f1": 78.8761565107113,
+    "eval_samples": 12246,
+    "eval_total": 11873
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ac594e443f8ac03ccb9e67ab6882420313a03145ea8d4e7b47427eaace6038
+size 437388081

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]",
+  "name_or_path": "allenai/scibert_scivocab_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": 0.9776556768279144,
+    "train_runtime": 8352.3756,
+    "train_samples": 132469,
+    "train_samples_per_second": 31.72,
+    "train_steps_per_second": 2.644
+}

trainer_state.json

@@ -0,0 +1,289 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 22080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.9320652173913043e-05,
+      "loss": 2.1276,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.8641304347826088e-05,
+      "loss": 1.6295,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.796195652173913e-05,
+      "loss": 1.4799,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.7282608695652175e-05,
+      "loss": 1.3996,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.6603260869565217e-05,
+      "loss": 1.388,
+      "step": 2500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.592391304347826e-05,
+      "loss": 1.3623,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.5244565217391304e-05,
+      "loss": 1.2824,
+      "step": 3500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.456521739130435e-05,
+      "loss": 1.2545,
+      "step": 4000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3885869565217394e-05,
+      "loss": 1.2108,
+      "step": 4500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.3206521739130436e-05,
+      "loss": 1.171,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.2527173913043478e-05,
+      "loss": 1.1727,
+      "step": 5500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1847826086956523e-05,
+      "loss": 1.146,
+      "step": 6000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.1168478260869565e-05,
+      "loss": 1.1192,
+      "step": 6500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.048913043478261e-05,
+      "loss": 1.1246,
+      "step": 7000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.9809782608695652e-05,
+      "loss": 1.116,
+      "step": 7500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.9130434782608694e-05,
+      "loss": 1.1,
+      "step": 8000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.845108695652174e-05,
+      "loss": 1.0572,
+      "step": 8500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.777173913043478e-05,
+      "loss": 1.0582,
+      "step": 9000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.7092391304347826e-05,
+      "loss": 1.0607,
+      "step": 9500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6413043478260868e-05,
+      "loss": 1.0371,
+      "step": 10000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5733695652173913e-05,
+      "loss": 1.0124,
+      "step": 10500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5054347826086957e-05,
+      "loss": 1.0183,
+      "step": 11000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.4375e-05,
+      "loss": 0.7648,
+      "step": 11500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.3695652173913042e-05,
+      "loss": 0.7755,
+      "step": 12000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.3016304347826088e-05,
+      "loss": 0.7331,
+      "step": 12500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.2336956521739131e-05,
+      "loss": 0.7311,
+      "step": 13000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1657608695652175e-05,
+      "loss": 0.7428,
+      "step": 13500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.0978260869565218e-05,
+      "loss": 0.705,
+      "step": 14000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.0298913043478262e-05,
+      "loss": 0.7386,
+      "step": 14500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 9.619565217391304e-06,
+      "loss": 0.7419,
+      "step": 15000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 8.940217391304347e-06,
+      "loss": 0.7521,
+      "step": 15500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 0.7241,
+      "step": 16000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.581521739130435e-06,
+      "loss": 0.7318,
+      "step": 16500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.9021739130434785e-06,
+      "loss": 0.7197,
+      "step": 17000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 6.222826086956522e-06,
+      "loss": 0.6928,
+      "step": 17500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.543478260869565e-06,
+      "loss": 0.6865,
+      "step": 18000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.864130434782609e-06,
+      "loss": 0.7075,
+      "step": 18500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 4.184782608695653e-06,
+      "loss": 0.6924,
+      "step": 19000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.5054347826086958e-06,
+      "loss": 0.7015,
+      "step": 19500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2.8260869565217393e-06,
+      "loss": 0.6896,
+      "step": 20000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.1467391304347824e-06,
+      "loss": 0.6933,
+      "step": 20500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.4673913043478262e-06,
+      "loss": 0.668,
+      "step": 21000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.880434782608695e-07,
+      "loss": 0.6788,
+      "step": 21500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0869565217391305e-07,
+      "loss": 0.6659,
+      "step": 22000
+    },
+    {
+      "epoch": 2.0,
+      "step": 22080,
+      "total_flos": 5.192058010209178e+16,
+      "train_loss": 0.9776556768279144,
+      "train_runtime": 8352.3756,
+      "train_samples_per_second": 31.72,
+      "train_steps_per_second": 2.644
+    }
+  ],
+  "max_steps": 22080,
+  "num_train_epochs": 2,
+  "total_flos": 5.192058010209178e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ebcf368765458c27f21f6738bdbe8fe69c4b5e6242e73cc1623b3f331331a2
+size 3439