add model

.gitignore

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

README.md

@@ -0,0 +1,74 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model_index:
+- name: qqp
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metric:
+      name: F1
+      type: f1
+      value: 0.8722569490623753
+---
+
+<!-- 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. -->
+
+# qqp
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE QQP dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3695
+- Accuracy: 0.9050
+- F1: 0.8723
+- Combined Score: 0.8886
+
+## 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: 64
+- 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 4.9.1
+- Pytorch 1.9.0+cu102
+- Datasets 1.10.2
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9049715557754143,
+    "eval_combined_score": 0.8886142524188948,
+    "eval_f1": 0.8722569490623753,
+    "eval_loss": 0.3695096969604492,
+    "eval_runtime": 207.4157,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 194.923,
+    "eval_steps_per_second": 24.367,
+    "train_loss": 0.1816996376236853,
+    "train_runtime": 16807.9309,
+    "train_samples": 363846,
+    "train_samples_per_second": 86.589,
+    "train_steps_per_second": 1.353
+}

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": "qqp",
+  "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 +1,11 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9049715557754143,
+    "eval_combined_score": 0.8886142524188948,
+    "eval_f1": 0.8722569490623753,
+    "eval_loss": 0.3695096969604492,
+    "eval_runtime": 207.4157,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 194.923,
+    "eval_steps_per_second": 24.367
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9f08c944128cb32b79ad2cc8bc8caa69157df9717769d2aae093ade9849c25
+size 46755537

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": 4.0,
+    "train_loss": 0.1816996376236853,
+    "train_runtime": 16807.9309,
+    "train_samples": 363846,
+    "train_samples_per_second": 86.589,
+    "train_steps_per_second": 1.353
+}

trainer_state.json

@@ -0,0 +1,295 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 22744,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.890080900457263e-05,
+      "loss": 0.4414,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.780161800914527e-05,
+      "loss": 0.3578,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.6702427013717904e-05,
+      "loss": 0.3321,
+      "step": 1500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.560323601829054e-05,
+      "loss": 0.3132,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.450404502286317e-05,
+      "loss": 0.3074,
+      "step": 2500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.3404854027435806e-05,
+      "loss": 0.2935,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.230566303200844e-05,
+      "loss": 0.2856,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.120647203658108e-05,
+      "loss": 0.2876,
+      "step": 4000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.010728104115371e-05,
+      "loss": 0.2751,
+      "step": 4500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.9008090045726345e-05,
+      "loss": 0.2709,
+      "step": 5000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.790889905029898e-05,
+      "loss": 0.266,
+      "step": 5500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.680970805487162e-05,
+      "loss": 0.2304,
+      "step": 6000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.571051705944425e-05,
+      "loss": 0.2132,
+      "step": 6500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 3.461132606401688e-05,
+      "loss": 0.2155,
+      "step": 7000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.351213506858952e-05,
+      "loss": 0.2111,
+      "step": 7500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.2412944073162155e-05,
+      "loss": 0.2164,
+      "step": 8000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 3.1313753077734785e-05,
+      "loss": 0.2107,
+      "step": 8500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.0214562082307425e-05,
+      "loss": 0.2149,
+      "step": 9000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.9115371086880054e-05,
+      "loss": 0.211,
+      "step": 9500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.8016180091452694e-05,
+      "loss": 0.2102,
+      "step": 10000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.6916989096025323e-05,
+      "loss": 0.2099,
+      "step": 10500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2.5817798100597963e-05,
+      "loss": 0.2047,
+      "step": 11000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 2.4718607105170596e-05,
+      "loss": 0.1848,
+      "step": 11500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 2.3619416109743232e-05,
+      "loss": 0.1338,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 2.2520225114315865e-05,
+      "loss": 0.1315,
+      "step": 12500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.14210341188885e-05,
+      "loss": 0.1354,
+      "step": 13000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.0321843123461134e-05,
+      "loss": 0.1422,
+      "step": 13500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.922265212803377e-05,
+      "loss": 0.1354,
+      "step": 14000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.8123461132606403e-05,
+      "loss": 0.1353,
+      "step": 14500
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.702427013717904e-05,
+      "loss": 0.1352,
+      "step": 15000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.5925079141751672e-05,
+      "loss": 0.1315,
+      "step": 15500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.4825888146324307e-05,
+      "loss": 0.134,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.3726697150896941e-05,
+      "loss": 0.1347,
+      "step": 16500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.2627506155469576e-05,
+      "loss": 0.1329,
+      "step": 17000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.1528315160042209e-05,
+      "loss": 0.085,
+      "step": 17500
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 1.0429124164614843e-05,
+      "loss": 0.0735,
+      "step": 18000
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 9.329933169187478e-06,
+      "loss": 0.0739,
+      "step": 18500
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 8.230742173760112e-06,
+      "loss": 0.0735,
+      "step": 19000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 7.131551178332748e-06,
+      "loss": 0.0718,
+      "step": 19500
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 6.032360182905382e-06,
+      "loss": 0.0708,
+      "step": 20000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 4.933169187478016e-06,
+      "loss": 0.0706,
+      "step": 20500
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 3.833978192050651e-06,
+      "loss": 0.0658,
+      "step": 21000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 2.7347871966232856e-06,
+      "loss": 0.0705,
+      "step": 21500
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.63559620119592e-06,
+      "loss": 0.0692,
+      "step": 22000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 5.364052057685544e-07,
+      "loss": 0.0641,
+      "step": 22500
+    },
+    {
+      "epoch": 4.0,
+      "step": 22744,
+      "total_flos": 8695228732968960.0,
+      "train_loss": 0.1816996376236853,
+      "train_runtime": 16807.9309,
+      "train_samples_per_second": 86.589,
+      "train_steps_per_second": 1.353
+    }
+  ],
+  "max_steps": 22744,
+  "num_train_epochs": 4,
+  "total_flos": 8695228732968960.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab74ea35cc43df1d47a80758bac1f3d772f30e225e40ab61a8208fa4557c908e
+size 2607