End of training

README.md

@@ -0,0 +1,86 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model-index:
+- name: bert-finetuned-mrpc
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8602941176470589
+    - name: F1
+      type: f1
+      value: 0.9032258064516129
+---
+
+<!-- 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. -->
+
+# bert-finetuned-mrpc
+
+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: 0.5152
+- Accuracy: 0.8603
+- F1: 0.9032
+- Combined Score: 0.8818
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Combined Score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
+| No log        | 1.0   | 230  | 0.3668          | 0.8431   | 0.8881 | 0.8656         |
+| No log        | 2.0   | 460  | 0.3751          | 0.8578   | 0.9017 | 0.8798         |
+| 0.4264        | 3.0   | 690  | 0.5152          | 0.8603   | 0.9032 | 0.8818         |
+
+
+### Framework versions
+
+- Transformers 4.11.0.dev0
+- Pytorch 1.8.1+cu111
+- Datasets 1.10.3.dev0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8602941176470589,
+    "eval_combined_score": 0.8817599620493359,
+    "eval_f1": 0.9032258064516129,
+    "eval_loss": 0.5152415037155151,
+    "eval_runtime": 0.681,
+    "eval_samples": 408,
+    "eval_samples_per_second": 599.092,
+    "eval_steps_per_second": 38.177,
+    "train_loss": 0.36320947287739186,
+    "train_runtime": 105.4434,
+    "train_samples": 3668,
+    "train_samples_per_second": 104.359,
+    "train_steps_per_second": 6.544
+}

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
+2021-09-14T13:10:06,cc9a5ccd-7eba-40e5-92ae-3a66f62862bb,codecarbon,108.45673489570618,0.002376985104054234,0.011293382035678484,United States,USA,new york,N,,

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8602941176470589,
+    "eval_combined_score": 0.8817599620493359,
+    "eval_f1": 0.9032258064516129,
+    "eval_loss": 0.5152415037155151,
+    "eval_runtime": 0.681,
+    "eval_samples": 408,
+    "eval_samples_per_second": 599.092,
+    "eval_steps_per_second": 38.177
+}

runs/Sep14_13-08-06_brahms/events.out.tfevents.1631639298.brahms.1547751.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:302b588ed56ac04dbedbf63a8af766ea275d1461710cf5f59e8706b9cebe72ad
-size 4697
+oid sha256:eacb80277a67ae78f10eac26ff7d05a2dad3bf2575f44883bcc77cec49585253
+size 5051

runs/Sep14_13-08-06_brahms/events.out.tfevents.1631639408.brahms.1547751.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c154852b8582d4a32049fe54e9756235538400310694e5f34fcbc2871f56c5
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.36320947287739186,
+    "train_runtime": 105.4434,
+    "train_samples": 3668,
+    "train_samples_per_second": 104.359,
+    "train_steps_per_second": 6.544
+}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "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": 1.0,
+      "eval_accuracy": 0.8431372549019608,
+      "eval_combined_score": 0.8656245715069245,
+      "eval_f1": 0.8881118881118882,
+      "eval_loss": 0.3667730391025543,
+      "eval_runtime": 0.621,
+      "eval_samples_per_second": 657.045,
+      "eval_steps_per_second": 41.87,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8578431372549019,
+      "eval_combined_score": 0.8797690262545697,
+      "eval_f1": 0.9016949152542373,
+      "eval_loss": 0.375055193901062,
+      "eval_runtime": 0.6266,
+      "eval_samples_per_second": 651.108,
+      "eval_steps_per_second": 41.492,
+      "step": 460
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3768115942028985e-05,
+      "loss": 0.4264,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8602941176470589,
+      "eval_combined_score": 0.8817599620493359,
+      "eval_f1": 0.9032258064516129,
+      "eval_loss": 0.5152415037155151,
+      "eval_runtime": 0.5833,
+      "eval_samples_per_second": 699.514,
+      "eval_steps_per_second": 44.577,
+      "step": 690
+    },
+    {
+      "epoch": 3.0,
+      "step": 690,
+      "total_flos": 723818515529728.0,
+      "train_loss": 0.36320947287739186,
+      "train_runtime": 105.4434,
+      "train_samples_per_second": 104.359,
+      "train_steps_per_second": 6.544
+    }
+  ],
+  "max_steps": 690,
+  "num_train_epochs": 3,
+  "total_flos": 723818515529728.0,
+  "trial_name": null,
+  "trial_params": null
+}