End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 license: apache-2.0
 tags:
 - generated_from_trainer
@@ -14,7 +16,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE MRPC
       type: glue
       config: mrpc
       split: validation
@@ -22,10 +24,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5514705882352942
+      value: 0.7083333333333334
     - name: F1
       type: f1
-      value: 0.6131078224101479
+      value: 0.8199697428139183
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sa_BERT_24_mrpc
 
-This model is a fine-tuned version of [gokuls/bert_base_24](https://huggingface.co/gokuls/bert_base_24) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_base_24](https://huggingface.co/gokuls/bert_base_24) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3865
-- Accuracy: 0.5515
-- F1: 0.6131
-- Combined Score: 0.5823
+- Loss: 0.6042
+- Accuracy: 0.7083
+- F1: 0.8200
+- Combined Score: 0.7642
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.7083333333333334,
+    "eval_combined_score": 0.7641515380736259,
+    "eval_f1": 0.8199697428139183,
+    "eval_loss": 0.6042224168777466,
+    "eval_runtime": 0.8567,
+    "eval_samples": 408,
+    "eval_samples_per_second": 476.264,
+    "eval_steps_per_second": 5.837,
+    "train_loss": 0.41005956005846333,
+    "train_runtime": 164.7992,
+    "train_samples": 3668,
+    "train_samples_per_second": 1112.87,
+    "train_steps_per_second": 11.833
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.7083333333333334,
+    "eval_combined_score": 0.7641515380736259,
+    "eval_f1": 0.8199697428139183,
+    "eval_loss": 0.6042224168777466,
+    "eval_runtime": 0.8567,
+    "eval_samples": 408,
+    "eval_samples_per_second": 476.264,
+    "eval_steps_per_second": 5.837
+}

logs/events.out.tfevents.1686863725.serv-3317.1921073.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1638ba986762939f9d83b33e6382bab36084ec6ac155229f608ddeb7d8181517
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.41005956005846333,
+    "train_runtime": 164.7992,
+    "train_samples": 3668,
+    "train_samples_per_second": 1112.87,
+    "train_steps_per_second": 11.833
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.6042224168777466,
+  "best_model_checkpoint": "sa_BERT_24_mrpc/checkpoint-39",
+  "epoch": 6.0,
+  "global_step": 234,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.6437,
+      "step": 39
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7083333333333334,
+      "eval_combined_score": 0.7641515380736259,
+      "eval_f1": 0.8199697428139183,
+      "eval_loss": 0.6042224168777466,
+      "eval_runtime": 0.8512,
+      "eval_samples_per_second": 479.345,
+      "eval_steps_per_second": 5.874,
+      "step": 39
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.5784,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6544117647058824,
+      "eval_combined_score": 0.6973716282092948,
+      "eval_f1": 0.7403314917127072,
+      "eval_loss": 0.6224242448806763,
+      "eval_runtime": 0.8574,
+      "eval_samples_per_second": 475.869,
+      "eval_steps_per_second": 5.832,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.4657,
+      "step": 117
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6740196078431373,
+      "eval_combined_score": 0.7278144016227182,
+      "eval_f1": 0.7816091954022989,
+      "eval_loss": 0.7196088433265686,
+      "eval_runtime": 0.8565,
+      "eval_samples_per_second": 476.373,
+      "eval_steps_per_second": 5.838,
+      "step": 117
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.3555,
+      "step": 156
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6348039215686274,
+      "eval_combined_score": 0.6882858429333605,
+      "eval_f1": 0.7417677642980934,
+      "eval_loss": 0.8928765654563904,
+      "eval_runtime": 0.8619,
+      "eval_samples_per_second": 473.392,
+      "eval_steps_per_second": 5.801,
+      "step": 156
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.2516,
+      "step": 195
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6078431372549019,
+      "eval_combined_score": 0.6535456287778268,
+      "eval_f1": 0.6992481203007518,
+      "eval_loss": 1.048213005065918,
+      "eval_runtime": 0.8612,
+      "eval_samples_per_second": 473.743,
+      "eval_steps_per_second": 5.806,
+      "step": 195
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.1654,
+      "step": 234
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5514705882352942,
+      "eval_combined_score": 0.5822892053227211,
+      "eval_f1": 0.6131078224101479,
+      "eval_loss": 1.386470913887024,
+      "eval_runtime": 0.8625,
+      "eval_samples_per_second": 473.04,
+      "eval_steps_per_second": 5.797,
+      "step": 234
+    },
+    {
+      "epoch": 6.0,
+      "step": 234,
+      "total_flos": 2895274095673344.0,
+      "train_loss": 0.41005956005846333,
+      "train_runtime": 164.7992,
+      "train_samples_per_second": 1112.87,
+      "train_steps_per_second": 11.833
+    }
+  ],
+  "max_steps": 1950,
+  "num_train_epochs": 50,
+  "total_flos": 2895274095673344.0,
+  "trial_name": null,
+  "trial_params": null
+}