Training in progress, step 500

README.md

@@ -0,0 +1,80 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model-index:
+- name: push-to-hub-test
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      config: mrpc
+      split: validation
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8676470588235294
+    - name: F1
+      type: f1
+      value: 0.9078498293515359
+---
+
+<!-- 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. -->
+
+# push-to-hub-test
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the GLUE MRPC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6255
+- Accuracy: 0.8676
+- F1: 0.9078
+- Combined Score: 0.8877
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.32.0.dev0
+- Pytorch 2.0.0+cu117
+- Datasets 2.14.4.dev0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8676470588235294,
+    "eval_combined_score": 0.8877484440875327,
+    "eval_f1": 0.9078498293515359,
+    "eval_loss": 0.6254646182060242,
+    "eval_runtime": 0.9668,
+    "eval_samples": 408,
+    "eval_samples_per_second": 422.028,
+    "eval_steps_per_second": 26.894,
+    "train_loss": 0.29736072982566947,
+    "train_runtime": 72.3445,
+    "train_samples": 3668,
+    "train_samples_per_second": 152.106,
+    "train_steps_per_second": 9.538
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "mrpc",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

emissions.csv

@@ -0,0 +1,12 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2022-06-10T06:57:35,eb65b40c-6656-492b-beab-b1127ec40a89,codecarbon,75.77277112007141,0.0019661329089992424,0.009341366942677192,United States,USA,new york,N,,
+2023-06-07T12:57:51,10bf2505-7043-4977-a3bd-89ff2bceb74c,codecarbon,22.494215726852417,0.0005877247722987192,0.002792360950887197,United States,USA,new york,N,,
+2023-06-07T12:59:15,27c1fb6c-5f93-4e1a-a0ac-c86241e84a50,codecarbon,70.80675888061523,0.0020041835812859015,0.009522150902204202,United States,USA,new york,N,,
+2023-06-07T13:02:28,943ea6b5-c22a-42ef-9877-f6599b3c7395,codecarbon,44.19557809829712,0.0009018572087676258,0.0042848472137548,United States,USA,new york,N,,
+2023-06-07T13:03:52,f3cf84e8-913c-4d05-aba1-1a4af046873d,codecarbon,70.99636244773865,0.0020228958118171324,0.009611055274288165,United States,USA,new york,N,,
+2023-06-07T13:04:57,ca4ee800-6554-4ea4-818a-44a382e60064,codecarbon,44.18032264709473,0.0009230705444922738,0.004385634679431778,United States,USA,new york,N,,
+2023-06-07T13:27:08,fa461c6a-6555-473b-aa79-a138281392a6,codecarbon,44.5587215423584,0.0008968433736060909,0.004261025795670793,United States,USA,new york,N,,
+2023-06-07T13:28:11,e36c4165-eb4f-4588-ae3b-e56e1a3280c2,codecarbon,44.47044777870178,0.0009021980585399627,0.004286466637742442,United States,USA,new york,N,,
+2023-06-07T13:33:28,27210e69-2b41-40a8-8f20-daea46e4428c,codecarbon,44.4998722076416,0.0008911166244071989,0.004233817225278285,United States,USA,new york,N,,
+2023-08-04T10:27:32,03f5fb31-9194-4a04-b842-0ba1aa7b8eec,codecarbon,72.91463541984558,0.002010806494296473,0.009553617269700523,United States,USA,new york,N,,
+2023-08-04T10:30:40,5757fa70-c58e-4185-8470-3e46d3363f15,codecarbon,75.35435104370117,0.0020779724772222426,0.009872732060823447,United States,USA,new york,N,,

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8676470588235294,
+    "eval_combined_score": 0.8877484440875327,
+    "eval_f1": 0.9078498293515359,
+    "eval_loss": 0.6254646182060242,
+    "eval_runtime": 0.9668,
+    "eval_samples": 408,
+    "eval_samples_per_second": 422.028,
+    "eval_steps_per_second": 26.894
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b311abbc8de524a975f2f205c66376fb0d9855e205e315d54c14bb6769dd2997
+size 433315633

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.29736072982566947,
+    "train_runtime": 72.3445,
+    "train_samples": 3668,
+    "train_samples_per_second": 152.106,
+    "train_steps_per_second": 9.538
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3768115942028985e-05,
+      "loss": 0.3782,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 690,
+      "total_flos": 723818513295360.0,
+      "train_loss": 0.29736072982566947,
+      "train_runtime": 72.3445,
+      "train_samples_per_second": 152.106,
+      "train_steps_per_second": 9.538
+    }
+  ],
+  "max_steps": 690,
+  "num_train_epochs": 3,
+  "total_flos": 723818513295360.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2007c2fd1134bc449e84210b49888da8ea596302ac9fd53aff2469ae577e540
+size 4091