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: mnli
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.8500813669650122
+---
+
+<!-- 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. -->
+
+# mnli
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE MNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5383
+- Accuracy: 0.8501
+
+## 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: 3e-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 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8500813669650122,
+    "eval_loss": 0.5383013486862183,
+    "eval_runtime": 50.6991,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 193.929,
+    "eval_steps_per_second": 24.241,
+    "train_loss": 0.3001841343599317,
+    "train_runtime": 18121.6674,
+    "train_samples": 392702,
+    "train_samples_per_second": 86.681,
+    "train_steps_per_second": 1.354
+}

config.json

@@ -0,0 +1,45 @@
+{
+  "_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": "mnli",
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": 4.0,
+    "eval_accuracy": 0.8500813669650122,
+    "eval_loss": 0.5383013486862183,
+    "eval_runtime": 50.6991,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 193.929,
+    "eval_steps_per_second": 24.241
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3228d57b4e7e1da04cc582bf139060a5afe2fd5bc2e4dc1f415e1ab4ddcf7c9a
+size 46758609

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": 0.3001841343599317,
+    "train_runtime": 18121.6674,
+    "train_samples": 392702,
+    "train_samples_per_second": 86.681,
+    "train_steps_per_second": 1.354
+}

trainer_state.json

@@ -0,0 +1,319 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 24544,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9388852672750976e-05,
+      "loss": 0.6805,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.877770534550196e-05,
+      "loss": 0.5507,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.8166558018252934e-05,
+      "loss": 0.5379,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.7555410691003913e-05,
+      "loss": 0.5057,
+      "step": 2000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.694426336375489e-05,
+      "loss": 0.4835,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.6333116036505867e-05,
+      "loss": 0.4697,
+      "step": 3000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.5721968709256846e-05,
+      "loss": 0.4676,
+      "step": 3500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.511082138200782e-05,
+      "loss": 0.4621,
+      "step": 4000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.4499674054758804e-05,
+      "loss": 0.4496,
+      "step": 4500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.388852672750978e-05,
+      "loss": 0.4382,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.3277379400260758e-05,
+      "loss": 0.4452,
+      "step": 5500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.2666232073011734e-05,
+      "loss": 0.4366,
+      "step": 6000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.2055084745762713e-05,
+      "loss": 0.3681,
+      "step": 6500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.144393741851369e-05,
+      "loss": 0.3505,
+      "step": 7000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.0832790091264667e-05,
+      "loss": 0.3528,
+      "step": 7500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.0221642764015646e-05,
+      "loss": 0.3458,
+      "step": 8000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.9610495436766625e-05,
+      "loss": 0.3527,
+      "step": 8500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.89993481095176e-05,
+      "loss": 0.3432,
+      "step": 9000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.838820078226858e-05,
+      "loss": 0.3428,
+      "step": 9500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.7777053455019558e-05,
+      "loss": 0.3478,
+      "step": 10000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.7165906127770537e-05,
+      "loss": 0.3424,
+      "step": 10500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.6554758800521512e-05,
+      "loss": 0.3433,
+      "step": 11000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.5943611473272488e-05,
+      "loss": 0.3417,
+      "step": 11500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.533246414602347e-05,
+      "loss": 0.3323,
+      "step": 12000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.4721316818774445e-05,
+      "loss": 0.2957,
+      "step": 12500
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.4110169491525424e-05,
+      "loss": 0.2283,
+      "step": 13000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.3499022164276401e-05,
+      "loss": 0.2252,
+      "step": 13500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.288787483702738e-05,
+      "loss": 0.2299,
+      "step": 14000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.2276727509778357e-05,
+      "loss": 0.2373,
+      "step": 14500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.1665580182529336e-05,
+      "loss": 0.2281,
+      "step": 15000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.1054432855280312e-05,
+      "loss": 0.2314,
+      "step": 15500
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.044328552803129e-05,
+      "loss": 0.2409,
+      "step": 16000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 9.83213820078227e-06,
+      "loss": 0.2375,
+      "step": 16500
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 9.220990873533247e-06,
+      "loss": 0.2308,
+      "step": 17000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 8.609843546284226e-06,
+      "loss": 0.2371,
+      "step": 17500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 7.998696219035203e-06,
+      "loss": 0.2328,
+      "step": 18000
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 7.38754889178618e-06,
+      "loss": 0.2145,
+      "step": 18500
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 6.776401564537158e-06,
+      "loss": 0.1336,
+      "step": 19000
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 6.165254237288136e-06,
+      "loss": 0.1356,
+      "step": 19500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 5.554106910039114e-06,
+      "loss": 0.1381,
+      "step": 20000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 4.942959582790091e-06,
+      "loss": 0.1343,
+      "step": 20500
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 4.331812255541069e-06,
+      "loss": 0.1385,
+      "step": 21000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 3.720664928292047e-06,
+      "loss": 0.1316,
+      "step": 21500
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 3.109517601043025e-06,
+      "loss": 0.1314,
+      "step": 22000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 2.498370273794003e-06,
+      "loss": 0.1221,
+      "step": 22500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.8872229465449805e-06,
+      "loss": 0.1301,
+      "step": 23000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.2760756192959583e-06,
+      "loss": 0.1249,
+      "step": 23500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 6.649282920469362e-07,
+      "loss": 0.1215,
+      "step": 24000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 5.378096479791395e-08,
+      "loss": 0.1225,
+      "step": 24500
+    },
+    {
+      "epoch": 4.0,
+      "step": 24544,
+      "total_flos": 9385760063993856.0,
+      "train_loss": 0.3001841343599317,
+      "train_runtime": 18121.6674,
+      "train_samples_per_second": 86.681,
+      "train_steps_per_second": 1.354
+    }
+  ],
+  "max_steps": 24544,
+  "num_train_epochs": 4,
+  "total_flos": 9385760063993856.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc30ee9a46e627693246aa5f5963c200aa9bc8ec1adf1061f9ebe32f77a41a8
+size 2607