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:
+- matthews_correlation
+model_index:
+- name: cola
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metric:
+      name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.5494768667363472
+---
+
+<!-- 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. -->
+
+# cola
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE COLA dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7552
+- Matthews Correlation: 0.5495
+
+## 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: 16
+- 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_loss": 0.7552478909492493,
+    "eval_matthews_correlation": 0.5494768667363472,
+    "eval_runtime": 17.5153,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 59.548,
+    "eval_steps_per_second": 7.479,
+    "train_loss": 0.3096321917025842,
+    "train_runtime": 1506.3037,
+    "train_samples": 8551,
+    "train_samples_per_second": 22.707,
+    "train_steps_per_second": 1.421
+}

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": "cola",
+  "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_loss": 0.7552478909492493,
+    "eval_matthews_correlation": 0.5494768667363472,
+    "eval_runtime": 17.5153,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 59.548,
+    "eval_steps_per_second": 7.479
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252285c7193f148de6ad7b3aaeb70ff3ead2c745bcf99faf4cdecc5ec20f7cee
+size 46755537

runs/Jul25_15-59-21_ba9036c8942d/1627228785.3837032/events.out.tfevents.1627228785.ba9036c8942d.497.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b564729c1220cee0e416722adeef2bcfcaa046ee2d7c43fee4c7da606286b7c
+size 4167

runs/Jul25_15-59-21_ba9036c8942d/events.out.tfevents.1627228785.ba9036c8942d.497.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ee7731330b9a07bde66c3c21e1ec9cce21f99758523b953fa9825536b8bbce
+size 4098

runs/Jul25_15-59-21_ba9036c8942d/events.out.tfevents.1627230309.ba9036c8942d.497.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f6fdb1499c198e5442296fb56f0663d5a6ae6a3901bf7a5d71d3c2e5d15cc9
+size 375

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": 0.3096321917025842,
+    "train_runtime": 1506.3037,
+    "train_samples": 8551,
+    "train_samples_per_second": 22.707,
+    "train_steps_per_second": 1.421
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 2140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.663551401869159e-06,
+      "loss": 0.5021,
+      "step": 500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.3271028037383174e-06,
+      "loss": 0.3487,
+      "step": 1000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.9906542056074766e-06,
+      "loss": 0.2435,
+      "step": 1500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 6.542056074766355e-07,
+      "loss": 0.1797,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "step": 2140,
+      "total_flos": 204352668149760.0,
+      "train_loss": 0.3096321917025842,
+      "train_runtime": 1506.3037,
+      "train_samples_per_second": 22.707,
+      "train_steps_per_second": 1.421
+    }
+  ],
+  "max_steps": 2140,
+  "num_train_epochs": 4,
+  "total_flos": 204352668149760.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b03e8908365b0f4fccfbeb4ac798af03d768a84cd8f96453300dcb077197904
+size 2607