End of training

.gitattributes

@@ -33,3 +33,7 @@ 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
+all_results.json filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.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

@@ -0,0 +1,51 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Yannis98/squad_albert_XXL_finetuned
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: tmp
+  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. -->
+
+# tmp
+
+This model is a fine-tuned version of [Yannis98/squad_albert_XXL_finetuned](https://huggingface.co/Yannis98/squad_albert_XXL_finetuned) on the squad 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: 32
+- eval_batch_size: 128
+- seed: 42
+- 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
+- num_epochs: 2.0
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c79fbcec9810803e5516f41fcc1bbf1ed2209164eb6d86af26fd713491b964
+size 17482733

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "Yannis98/squad_albert_XXL_finetuned",
+  "architectures": [
+    "AlbertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-12,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 64,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea411e5fcd1d9572fe2dc9ded0d7b84f38e72f5d6ce01871f20e94fdd96325a2
+size 66082932

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "eval_exact_match": 88.64711447492904,
+    "eval_f1": 94.74429831112143,
+    "eval_model_preparation_time": 0.0008,
+    "eval_runtime": 592.7623,
+    "eval_samples": 10808,
+    "eval_samples_per_second": 18.233,
+    "eval_steps_per_second": 0.143
+}

full_predict_tr_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d2ab3b08be3c34eee6a0633e9075ab9cc863dc868e1ba3d8d6ec5d5f45d037
+size 15599087

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26bbe49807c22bf7a2581d98bd28ce1552dee917c7b3437f84d30428f90ad76a
+size 823293160

predict_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea411e5fcd1d9572fe2dc9ded0d7b84f38e72f5d6ce01871f20e94fdd96325a2
+size 66082932

predict_tr_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_samples_tr": 88638,
+    "test_exact_match": 89.94965695955433,
+    "test_f1": 96.25404704412455,
+    "test_model_preparation_time": 0.0008,
+    "test_runtime": 4916.4105,
+    "test_samples_per_second": 18.029,
+    "test_steps_per_second": 0.141
+}

predict_val_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_samples_val": 10808,
+    "test_exact_match": 88.64711447492904,
+    "test_f1": 94.74429831112143,
+    "test_model_preparation_time": 0.0008,
+    "test_runtime": 591.1148,
+    "test_samples_per_second": 18.284,
+    "test_steps_per_second": 0.144
+}

runs/Feb10_10-34-46_xgpi1/events.out.tfevents.1739155577.xgpi1.5922.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:107d44dde820f256ddf2d3e4545e4c3203594de79c881c4c8d21cb61c9724083
+size 410

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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,
+    "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "max_length": 384,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "stride": 128,
+  "tokenizer_class": "AlbertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec561c30308bd718e51b243992b37123262681c04ec8b0a4ad87d61ad7484c0
+size 5368