End of training

.gitattributes

@@ -34,3 +34,6 @@ saved_model/**/* 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 filter=lfs diff=lfs merge=lfs -text
+full_predict_tr_results.json filter=lfs diff=lfs merge=lfs -text
+predict_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,21 +1,22 @@
 ---
+library_name: transformers
 license: apache-2.0
-base_model: albert/albert-xxlarge-v2
+base_model: Yannis98/XXL-Albert-squadv2
 tags:
 - generated_from_trainer
 datasets:
-- squad_v2
+- rajpurkar/squad_v2
 model-index:
-- name: XXLarge_Albert
+- name: XXL-Albert-squadv2
   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. -->
 
-# XXLarge_Albert
+# XXL-Albert-squadv2
 
-This model is a fine-tuned version of [albert/albert-xxlarge-v2](https://huggingface.co/albert/albert-xxlarge-v2) on the squad_v2 dataset.
+This model is a fine-tuned version of [Yannis98/XXL-Albert-squadv2](https://huggingface.co/Yannis98/XXL-Albert-squadv2) on the rajpurkar/squad_v2 dataset.
 
 ## Model description
 
@@ -34,22 +35,17 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 12
-- eval_batch_size: 8
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 512
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 2.0
 
-### Training results
-
-
-
 ### Framework versions
 
-- Transformers 4.45.0.dev0
-- Pytorch 2.2.2+cu121
-- Datasets 2.19.2
-- Tokenizers 0.19.1
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.21.0

all_results.json

@@ -1,26 +1,3 @@
-{
-    "epoch": 2.0,
-    "eval_HasAns_exact": 84.26113360323886,
-    "eval_HasAns_f1": 90.65827763075589,
-    "eval_HasAns_total": 5928,
-    "eval_NoAns_exact": 87.82169890664424,
-    "eval_NoAns_f1": 87.82169890664424,
-    "eval_NoAns_total": 5945,
-    "eval_best_exact": 86.04396529941884,
-    "eval_best_exact_thresh": 0.0,
-    "eval_best_f1": 89.23795753348925,
-    "eval_best_f1_thresh": 0.0,
-    "eval_exact": 86.04396529941884,
-    "eval_f1": 89.23795753348945,
-    "eval_runtime": 1439.2108,
-    "eval_samples": 12171,
-    "eval_samples_per_second": 8.457,
-    "eval_steps_per_second": 1.058,
-    "eval_total": 11873,
-    "total_flos": 1.2277795031512474e+17,
-    "train_loss": 1.0133790219709247,
-    "train_runtime": 87315.1804,
-    "train_samples": 131958,
-    "train_samples_per_second": 3.023,
-    "train_steps_per_second": 0.252
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ee959ed73162412986828691253a3330e292cecbf0c74c7a9b4153d8cf166b
+size 23490140

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "albert/albert-xxlarge-v2",
+  "_name_or_path": "Yannis98/XXL-Albert-squadv2",
   "architectures": [
     "AlbertForQuestionAnswering"
   ],
@@ -28,7 +28,7 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.45.0.dev0",
+  "transformers_version": "4.47.1",
   "type_vocab_size": 2,
   "vocab_size": 30000
 }

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48398dd4307e1e43816fd7fd56807c5c4d32ebcf22024eef03880c99bde5f9fd
-size 56467143
+oid sha256:2dbfefa58da726f80c7f09162f63d79da572e740f1cb43af45e2c8612190540a
+size 75943289

eval_results.json

@@ -1,5 +1,4 @@
 {
-    "epoch": 2.0,
     "eval_HasAns_exact": 84.26113360323886,
     "eval_HasAns_f1": 90.65827763075589,
     "eval_HasAns_total": 5928,
@@ -12,9 +11,10 @@
     "eval_best_f1_thresh": 0.0,
     "eval_exact": 86.04396529941884,
     "eval_f1": 89.23795753348945,
-    "eval_runtime": 1439.2108,
+    "eval_model_preparation_time": 0.0008,
+    "eval_runtime": 664.4278,
     "eval_samples": 12171,
-    "eval_samples_per_second": 8.457,
-    "eval_steps_per_second": 1.058,
+    "eval_samples_per_second": 18.318,
+    "eval_steps_per_second": 0.036,
     "eval_total": 11873
 }

full_predict_tr_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95acd24386c013e334184e9e749d41c9c957dda820f1c44282431354601471a2
+size 21570994

predict_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbfefa58da726f80c7f09162f63d79da572e740f1cb43af45e2c8612190540a
+size 75943289

predict_tr_results.json

@@ -0,0 +1,20 @@
+{
+    "predict_samples_tr": 131958,
+    "test_HasAns_exact": 88.38760207783831,
+    "test_HasAns_f1": 95.34688428820678,
+    "test_HasAns_total": 86821,
+    "test_NoAns_exact": 98.59533771667662,
+    "test_NoAns_f1": 98.59533771667662,
+    "test_NoAns_total": 43498,
+    "test_best_exact": 91.79705184969191,
+    "test_best_exact_thresh": 0.0,
+    "test_best_f1": 96.43345821244162,
+    "test_best_f1_thresh": 0.0,
+    "test_exact": 91.79474980624468,
+    "test_f1": 96.43115616899117,
+    "test_model_preparation_time": 0.0008,
+    "test_runtime": 7283.2943,
+    "test_samples_per_second": 18.118,
+    "test_steps_per_second": 0.035,
+    "test_total": 130319
+}

predict_val_results.json

@@ -0,0 +1,20 @@
+{
+    "predict_samples_val": 12171,
+    "test_HasAns_exact": 84.26113360323886,
+    "test_HasAns_f1": 90.65827763075589,
+    "test_HasAns_total": 5928,
+    "test_NoAns_exact": 87.82169890664424,
+    "test_NoAns_f1": 87.82169890664424,
+    "test_NoAns_total": 5945,
+    "test_best_exact": 86.04396529941884,
+    "test_best_exact_thresh": 0.0,
+    "test_best_f1": 89.23795753348925,
+    "test_best_f1_thresh": 0.0,
+    "test_exact": 86.04396529941884,
+    "test_f1": 89.23795753348945,
+    "test_model_preparation_time": 0.0008,
+    "test_runtime": 665.0866,
+    "test_samples_per_second": 18.3,
+    "test_steps_per_second": 0.036,
+    "test_total": 11873
+}

runs/Feb11_13-24-54_xgpi7/events.out.tfevents.1739252278.xgpi7.27787.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c3fda2e43affd87fcf06abe9f8b799a1bda01c8d5e399f519d44c57494b4a6
+size 971

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "[MASK]",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "[SEP]",
-  "unk_token": "<unk>"
+  "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
+  }
 }

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,

tokenizer_config.json

@@ -46,6 +46,7 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "eos_token": "[SEP]",
+  "extra_special_tokens": {},
   "keep_accents": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873097dc6d1faf0b18613bd4006fd5ee1633ecc4b1762cead7de0247012ff145
-size 5304
+oid sha256:6e2041d4730bf26252e172fbca22eb69dfcf6cd9ae2b0f236d05df53c0d23427
+size 5432