add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,71 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model_index:
+- name: qnli
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.642504118616145
+---
+
+<!-- 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. -->
+
+# qnli
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE QNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6284
+- Accuracy: 0.6425
+
+## 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: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 0.001
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.2
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.0,
+    "eval_accuracy": 0.642504118616145,
+    "eval_loss": 0.6284383535385132,
+    "eval_runtime": 27.9064,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 195.761,
+    "eval_steps_per_second": 24.475,
+    "train_loss": 0.6153523921966553,
+    "train_runtime": 1.5743,
+    "train_samples": 104743,
+    "train_samples_per_second": 66.532,
+    "train_steps_per_second": 2.541
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "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,
+  "finetuning_task": "qnli",
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.0,
+    "eval_accuracy": 0.642504118616145,
+    "eval_loss": 0.6284383535385132,
+    "eval_runtime": 27.9064,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 195.761,
+    "eval_steps_per_second": 24.475
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae50e44ae6c4889694abbe34789e6aabd80d3015327c765d912c85905c45a160
+size 46755537

runs/Jul27_12-11-25_nlp992/1627387922.7176468/events.out.tfevents.1627387922.nlp992

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b1785a5678bffc787108377246323f5272904213ecb924bc2c2d7e5c337104
+size 4000

runs/Jul27_12-11-25_nlp992/events.out.tfevents.1627387922.nlp992

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0008a7d5aab7019d9b81549ba08d024fdd8641bae1c431af5a1abe557c37f37
+size 7546

runs/Jul27_12-11-25_nlp992/events.out.tfevents.1627393044.nlp992

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd47d89ca7f0f5441388c1177163c6147e2b26ee594721c4fe051491fb847927
+size 88

runs/Jul27_14-07-08_nlp992/1627394846.6303906/events.out.tfevents.1627394846.nlp992

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90058a43100ee18a6d59e28231996eae915b74b5aa5ba923ed6d053d72a52798
+size 4000

runs/Jul27_14-07-08_nlp992/events.out.tfevents.1627394846.nlp992

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e200671ae678b4689031a5355e08e67155e8ea35a23447ae06848bcbd562b6df
+size 3459

runs/Jul27_14-07-08_nlp992/events.out.tfevents.1627394887.nlp992

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da12934f4f68e4e0d23bbd6bd227aa9b2a535ebb6062fa859e4a942dd7a8f368
+size 87

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 0.6153523921966553,
+    "train_runtime": 1.5743,
+    "train_samples": 104743,
+    "train_samples_per_second": 66.532,
+    "train_steps_per_second": 2.541
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0012217470983506415,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "step": 4,
+      "total_flos": 764739256320.0,
+      "train_loss": 0.6153523921966553,
+      "train_runtime": 1.5743,
+      "train_samples_per_second": 66.532,
+      "train_steps_per_second": 2.541
+    }
+  ],
+  "max_steps": 4,
+  "num_train_epochs": 1,
+  "total_flos": 764739256320.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae27f71105e7743e6d9c42fd3887cf54f03f8d711b08b7fe00d90710bc91811
+size 2607