End of training

.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 +1,50 @@
+---
+license: mit
+base_model: prajjwal1/bert-tiny
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: V1
+  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. -->
+
+# V1
+
+This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) 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: 5e-05
+- train_batch_size: 96
+- eval_batch_size: 12
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,19 @@
+{
+    "eval_HasAns_exact": 0.0,
+    "eval_HasAns_f1": 4.14210369723646,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 19.83179142136249,
+    "eval_NoAns_f1": 19.83179142136249,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 50.07159100480081,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 50.081405424967926,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 9.9300934894298,
+    "eval_f1": 11.998179964391293,
+    "eval_runtime": 247.8052,
+    "eval_samples": 12134,
+    "eval_samples_per_second": 48.966,
+    "eval_steps_per_second": 4.084,
+    "eval_total": 11873
+}

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "VenkatManda/V1",
+  "_name_or_path": "prajjwal1/bert-tiny",
   "architectures": [
     "BertForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.3,
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 128,
   "initializer_range": 0.02,
   "intermediate_size": 512,
@@ -18,7 +18,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.37.0.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:a986d1ec9e11c91463d2b63f2ea2ff33d6ec81fd6201faa4707ec5ce2168c8be
+size 21812970

eval_results.json

@@ -0,0 +1,19 @@
+{
+    "eval_HasAns_exact": 0.0,
+    "eval_HasAns_f1": 4.14210369723646,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 19.83179142136249,
+    "eval_NoAns_f1": 19.83179142136249,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 50.07159100480081,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 50.081405424967926,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 9.9300934894298,
+    "eval_f1": 11.998179964391293,
+    "eval_runtime": 247.8052,
+    "eval_samples": 12134,
+    "eval_samples_per_second": 48.966,
+    "eval_steps_per_second": 4.084,
+    "eval_total": 11873
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52262c0b41bda521bbea4f8620ecf690586333a9955d6a4fa0f9389de9237d1
+oid sha256:532d2ec490653061f5bdf3eb184e58d2be566b8e96c010b6d76a3eb75bd7263f
 size 17483080

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 384,
+    "strategy": "OnlySecond",
+    "stride": 128
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 384
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437e0695fb8e79ab7fc2dc357b1a230b757ffb22d3a04433e16268de0466951d
-size 4728
+oid sha256:5cdace9ec738f1bfc2f5d803c733ebd0a623e89b53e4c48b568d22841517a874
+size 4664