End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -12,7 +14,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE QNLI
       type: glue
       config: qnli
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5892366831411312
+      value: 0.5967417170053084
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_new_pretrain_48_qnli
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_48) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6712
-- Accuracy: 0.5892
+- Loss: 0.6635
+- Accuracy: 0.5967
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5967417170053084,
+    "eval_loss": 0.663513720035553,
+    "eval_runtime": 8.8432,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 617.761,
+    "eval_steps_per_second": 4.862,
+    "train_loss": 0.664185315552503,
+    "train_runtime": 3055.0756,
+    "train_samples": 104743,
+    "train_samples_per_second": 1714.246,
+    "train_steps_per_second": 13.404
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.5967417170053084,
+    "eval_loss": 0.663513720035553,
+    "eval_runtime": 8.8432,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 617.761,
+    "eval_steps_per_second": 4.862
+}

logs/events.out.tfevents.1686037379.serv-9207.2387813.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35ac56fb383629d58e5d1c9906baf4ef3c5b27ac63613975f46f77e2a24556d
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.664185315552503,
+    "train_runtime": 3055.0756,
+    "train_samples": 104743,
+    "train_samples_per_second": 1714.246,
+    "train_steps_per_second": 13.404
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.663513720035553,
+  "best_model_checkpoint": "hBERTv2_new_pretrain_48_qnli/checkpoint-819",
+  "epoch": 6.0,
+  "global_step": 4914,
+  "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": 0.6834,
+      "step": 819
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5967417170053084,
+      "eval_loss": 0.663513720035553,
+      "eval_runtime": 8.9415,
+      "eval_samples_per_second": 610.973,
+      "eval_steps_per_second": 4.809,
+      "step": 819
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.6634,
+      "step": 1638
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5930807248764415,
+      "eval_loss": 0.6695936918258667,
+      "eval_runtime": 8.9249,
+      "eval_samples_per_second": 612.104,
+      "eval_steps_per_second": 4.818,
+      "step": 1638
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6597,
+      "step": 2457
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6013179571663921,
+      "eval_loss": 0.6701249480247498,
+      "eval_runtime": 8.9514,
+      "eval_samples_per_second": 610.298,
+      "eval_steps_per_second": 4.804,
+      "step": 2457
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.6607,
+      "step": 3276
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5875892366831411,
+      "eval_loss": 0.6779921650886536,
+      "eval_runtime": 8.9387,
+      "eval_samples_per_second": 611.16,
+      "eval_steps_per_second": 4.811,
+      "step": 3276
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.6602,
+      "step": 4095
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5857587406187077,
+      "eval_loss": 0.6902507543563843,
+      "eval_runtime": 8.9276,
+      "eval_samples_per_second": 611.919,
+      "eval_steps_per_second": 4.816,
+      "step": 4095
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.6577,
+      "step": 4914
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5892366831411312,
+      "eval_loss": 0.6711513996124268,
+      "eval_runtime": 8.9297,
+      "eval_samples_per_second": 611.777,
+      "eval_steps_per_second": 4.815,
+      "step": 4914
+    },
+    {
+      "epoch": 6.0,
+      "step": 4914,
+      "total_flos": 9.19680230400983e+16,
+      "train_loss": 0.664185315552503,
+      "train_runtime": 3055.0756,
+      "train_samples_per_second": 1714.246,
+      "train_steps_per_second": 13.404
+    }
+  ],
+  "max_steps": 40950,
+  "num_train_epochs": 50,
+  "total_flos": 9.19680230400983e+16,
+  "trial_name": null,
+  "trial_params": null
+}