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: 0.7752150832875709
+      value: 0.7935200439319056
 ---
 
 <!-- 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. -->
 
 # hBERTv1_new_pretrain_w_init_48_qnli
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6240
-- Accuracy: 0.7752
+- Loss: 0.4527
+- Accuracy: 0.7935
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.7935200439319056,
+    "eval_loss": 0.4527376592159271,
+    "eval_runtime": 9.9513,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 548.972,
+    "eval_steps_per_second": 4.321,
+    "train_loss": 0.35937960372011885,
+    "train_runtime": 5750.0945,
+    "train_samples": 104743,
+    "train_samples_per_second": 910.794,
+    "train_steps_per_second": 7.122
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.7935200439319056,
+    "eval_loss": 0.4527376592159271,
+    "eval_runtime": 9.9513,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 548.972,
+    "eval_steps_per_second": 4.321
+}

logs/events.out.tfevents.1686040975.serv-9207.2389173.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a590d4e2e181747137c10ce7f6c810c2e444e64d73522d91f1978246b2e5b482
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.35937960372011885,
+    "train_runtime": 5750.0945,
+    "train_samples": 104743,
+    "train_samples_per_second": 910.794,
+    "train_steps_per_second": 7.122
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.4527376592159271,
+  "best_model_checkpoint": "hBERTv1_new_pretrain_w_init_48_qnli/checkpoint-4095",
+  "epoch": 10.0,
+  "global_step": 8190,
+  "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": 0.615,
+      "step": 819
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7040087863811093,
+      "eval_loss": 0.5774398446083069,
+      "eval_runtime": 10.067,
+      "eval_samples_per_second": 542.663,
+      "eval_steps_per_second": 4.271,
+      "step": 819
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.5092,
+      "step": 1638
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7818048691195314,
+      "eval_loss": 0.4735040068626404,
+      "eval_runtime": 10.1673,
+      "eval_samples_per_second": 537.309,
+      "eval_steps_per_second": 4.229,
+      "step": 1638
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.4554,
+      "step": 2457
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7861980596741717,
+      "eval_loss": 0.466993510723114,
+      "eval_runtime": 10.0759,
+      "eval_samples_per_second": 542.183,
+      "eval_steps_per_second": 4.268,
+      "step": 2457
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.4041,
+      "step": 3276
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7807065714808713,
+      "eval_loss": 0.4881279766559601,
+      "eval_runtime": 10.0028,
+      "eval_samples_per_second": 546.149,
+      "eval_steps_per_second": 4.299,
+      "step": 3276
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.3567,
+      "step": 4095
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7935200439319056,
+      "eval_loss": 0.4527376592159271,
+      "eval_runtime": 10.0559,
+      "eval_samples_per_second": 543.261,
+      "eval_steps_per_second": 4.276,
+      "step": 4095
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.3218,
+      "step": 4914
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7819879187259747,
+      "eval_loss": 0.5325487852096558,
+      "eval_runtime": 10.0427,
+      "eval_samples_per_second": 543.975,
+      "eval_steps_per_second": 4.282,
+      "step": 4914
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.44e-05,
+      "loss": 0.2864,
+      "step": 5733
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7829031667581915,
+      "eval_loss": 0.5454465746879578,
+      "eval_runtime": 10.0511,
+      "eval_samples_per_second": 543.525,
+      "eval_steps_per_second": 4.278,
+      "step": 5733
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 0.2482,
+      "step": 6552
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7700896943071572,
+      "eval_loss": 0.5525962114334106,
+      "eval_runtime": 10.0206,
+      "eval_samples_per_second": 545.178,
+      "eval_steps_per_second": 4.291,
+      "step": 6552
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 3.28e-05,
+      "loss": 0.2146,
+      "step": 7371
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7834523155775215,
+      "eval_loss": 0.5931808948516846,
+      "eval_runtime": 10.0523,
+      "eval_samples_per_second": 543.455,
+      "eval_steps_per_second": 4.278,
+      "step": 7371
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.1825,
+      "step": 8190
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.7752150832875709,
+      "eval_loss": 0.6240017414093018,
+      "eval_runtime": 10.0826,
+      "eval_samples_per_second": 541.827,
+      "eval_steps_per_second": 4.265,
+      "step": 8190
+    },
+    {
+      "epoch": 10.0,
+      "step": 8190,
+      "total_flos": 1.5512100096966656e+17,
+      "train_loss": 0.35937960372011885,
+      "train_runtime": 5750.0945,
+      "train_samples_per_second": 910.794,
+      "train_steps_per_second": 7.122
+    }
+  ],
+  "max_steps": 40950,
+  "num_train_epochs": 50,
+  "total_flos": 1.5512100096966656e+17,
+  "trial_name": null,
+  "trial_params": null
+}