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: testing
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metric:
+      name: F1
+      type: f1
+      value: 0.8104956268221574
+---
+
+<!-- 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. -->
+
+# testing
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE MRPC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6644
+- Accuracy: 0.6814
+- F1: 0.8105
+- Combined Score: 0.7459
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 10
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.10.0.dev0
+- Pytorch 1.9.0+cu111
+- Datasets 1.11.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.0,
+    "eval_accuracy": 0.6813725490196079,
+    "eval_combined_score": 0.7459340879208827,
+    "eval_f1": 0.8104956268221574,
+    "eval_loss": 0.6643973588943481,
+    "eval_runtime": 1.3324,
+    "eval_samples": 408,
+    "eval_samples_per_second": 306.21,
+    "eval_steps_per_second": 38.276,
+    "train_loss": 0.6649961948394776,
+    "train_runtime": 0.4443,
+    "train_samples": 3668,
+    "train_samples_per_second": 22.507,
+    "train_steps_per_second": 22.507
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "mrpc",
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0.dev0",
+  "vocab_size": 30522
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2021-09-22T14:49:03,22510de0-5f5a-4992-a10f-5f87ce9f9508,codecarbon,3.48142671585083,2.050872917901026e-06,9.743978340031914e-06,United States,USA,new york,N,,

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 0.0,
+    "eval_accuracy": 0.6813725490196079,
+    "eval_combined_score": 0.7459340879208827,
+    "eval_f1": 0.8104956268221574,
+    "eval_loss": 0.6643973588943481,
+    "eval_runtime": 1.3324,
+    "eval_samples": 408,
+    "eval_samples_per_second": 306.21,
+    "eval_steps_per_second": 38.276
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014324fc4acbc63977f6f32eab74752231a997514ab5122c50b13d62c4becf2c
+size 267860081

runs/Sep22_14-48-48_Beaver/1632336539.9057102/events.out.tfevents.1632336539.Beaver.1803589.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5658a63013549ed5b7ea37a14bccfd55cd01c67b9d19de97108ab55470564db9
+size 4170

runs/Sep22_14-48-48_Beaver/events.out.tfevents.1632336539.Beaver.1803589.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48508dbc11a055495d9474667a53e358c4266de6fbc8e5d2049f41ecab7253c
+size 3202

runs/Sep22_14-48-48_Beaver/events.out.tfevents.1632336545.Beaver.1803589.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a24a52d0acdc7a005b1ec57c274a841f4f62d6021851a799153bbeac126ccf4
+size 459

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 0.6649961948394776,
+    "train_runtime": 0.4443,
+    "train_samples": 3668,
+    "train_samples_per_second": 22.507,
+    "train_steps_per_second": 22.507
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0027262813522355507,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "step": 10,
+      "total_flos": 331168496640.0,
+      "train_loss": 0.6649961948394776,
+      "train_runtime": 0.4443,
+      "train_samples_per_second": 22.507,
+      "train_steps_per_second": 22.507
+    }
+  ],
+  "max_steps": 10,
+  "num_train_epochs": 1,
+  "total_flos": 331168496640.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f5afd8071cb5726167ecfa873079d6dd823e50c1ea1a06e51b530298b4d840
+size 2607