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: sst2
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.9231651376146789
+---
+
+<!-- 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. -->
+
+# sst2
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE SST2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3808
+- Accuracy: 0.9232
+
+## 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: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.9.0
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.2
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9231651376146789,
+    "eval_loss": 0.3807859718799591,
+    "eval_runtime": 8.172,
+    "eval_samples": 872,
+    "eval_samples_per_second": 106.705,
+    "eval_steps_per_second": 13.338,
+    "train_loss": 0.14146648778485005,
+    "train_runtime": 6028.0345,
+    "train_samples": 67349,
+    "train_samples_per_second": 44.691,
+    "train_steps_per_second": 1.397
+}

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": "sst2",
+  "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": "4.9.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9231651376146789,
+    "eval_loss": 0.3807859718799591,
+    "eval_runtime": 8.172,
+    "eval_samples": 872,
+    "eval_samples_per_second": 106.705,
+    "eval_steps_per_second": 13.338
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c8d97db2205a5d6748479b105db67fe1c56466d78eb652d77005387f602900
+size 46755537

runs/Jul26_12-21-38_578c7831d7ba/1627302117.7817998/events.out.tfevents.1627302117.578c7831d7ba.805.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21bbb4b3b6e2eb5f4709437218c693f53720cd8bef9c0f25829cff58af7e70b
+size 4167

runs/Jul26_12-21-38_578c7831d7ba/events.out.tfevents.1627302117.578c7831d7ba.805.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1e2e5113865b3ab8b85247a4e1d39a44c0da049fcf348b15507337abade0fa
+size 5982

runs/Jul26_12-21-38_578c7831d7ba/events.out.tfevents.1627308154.578c7831d7ba.805.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834d9f777746d25b9cfdaa49b6ed5c3afd8fc3c54f71aa3ac5e411386e6a46fe
+size 363

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}}

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": 4.0,
+    "train_loss": 0.14146648778485005,
+    "train_runtime": 6028.0345,
+    "train_samples": 67349,
+    "train_samples_per_second": 44.691,
+    "train_steps_per_second": 1.397
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 8420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.406175771971498e-06,
+      "loss": 0.3692,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 8.812351543942995e-06,
+      "loss": 0.2463,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 8.21852731591449e-06,
+      "loss": 0.2089,
+      "step": 1500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.624703087885986e-06,
+      "loss": 0.1926,
+      "step": 2000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.030878859857483e-06,
+      "loss": 0.1504,
+      "step": 2500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 6.437054631828979e-06,
+      "loss": 0.1411,
+      "step": 3000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 5.843230403800475e-06,
+      "loss": 0.1425,
+      "step": 3500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 5.2494061757719716e-06,
+      "loss": 0.1351,
+      "step": 4000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.6555819477434686e-06,
+      "loss": 0.1067,
+      "step": 4500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.061757719714965e-06,
+      "loss": 0.1002,
+      "step": 5000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 3.467933491686461e-06,
+      "loss": 0.1048,
+      "step": 5500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.874109263657958e-06,
+      "loss": 0.1099,
+      "step": 6000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 2.280285035629454e-06,
+      "loss": 0.0836,
+      "step": 6500
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 1.6864608076009503e-06,
+      "loss": 0.071,
+      "step": 7000
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.0926365795724466e-06,
+      "loss": 0.0729,
+      "step": 7500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 4.988123515439431e-07,
+      "loss": 0.0837,
+      "step": 8000
+    },
+    {
+      "epoch": 4.0,
+      "step": 8420,
+      "total_flos": 1609513255434240.0,
+      "train_loss": 0.14146648778485005,
+      "train_runtime": 6028.0345,
+      "train_samples_per_second": 44.691,
+      "train_steps_per_second": 1.397
+    }
+  ],
+  "max_steps": 8420,
+  "num_train_epochs": 4,
+  "total_flos": 1609513255434240.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b388633199c3ec69f5d793e929089e5be4a7e02891c673ec492629445a5e1ba4
+size 2607