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 SST2
       type: glue
       config: sst2
       split: validation
@@ -20,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.786697247706422
+      value: 0.8084862385321101
 ---
 
 <!-- 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_48_sst2
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_48) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_48) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6457
-- Accuracy: 0.7867
+- Loss: 0.4843
+- Accuracy: 0.8085
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8084862385321101,
+    "eval_loss": 0.4843260943889618,
+    "eval_runtime": 1.5731,
+    "eval_samples": 872,
+    "eval_samples_per_second": 554.328,
+    "eval_steps_per_second": 4.45,
+    "train_loss": 0.20944157648056388,
+    "train_runtime": 2148.5153,
+    "train_samples": 67349,
+    "train_samples_per_second": 1567.338,
+    "train_steps_per_second": 12.264
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8084862385321101,
+    "eval_loss": 0.4843260943889618,
+    "eval_runtime": 1.5731,
+    "eval_samples": 872,
+    "eval_samples_per_second": 554.328,
+    "eval_steps_per_second": 4.45
+}

logs/events.out.tfevents.1686032892.serv-9219.1456809.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e35423ba746da93903c60f008cb0eeecf5cc9a879e708a7e12d1fa7fee1ad9
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.20944157648056388,
+    "train_runtime": 2148.5153,
+    "train_samples": 67349,
+    "train_samples_per_second": 1567.338,
+    "train_steps_per_second": 12.264
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 0.4843260943889618,
+  "best_model_checkpoint": "hBERTv1_new_pretrain_48_sst2/checkpoint-527",
+  "epoch": 6.0,
+  "global_step": 3162,
+  "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": 0.3894,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 0.4843260943889618,
+      "eval_runtime": 1.5514,
+      "eval_samples_per_second": 562.079,
+      "eval_steps_per_second": 4.512,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.2353,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7947247706422018,
+      "eval_loss": 0.6085422039031982,
+      "eval_runtime": 1.5494,
+      "eval_samples_per_second": 562.793,
+      "eval_steps_per_second": 4.518,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.76e-05,
+      "loss": 0.1917,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 0.5546697378158569,
+      "eval_runtime": 1.56,
+      "eval_samples_per_second": 558.99,
+      "eval_steps_per_second": 4.487,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.1653,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 0.6457037925720215,
+      "eval_runtime": 1.5511,
+      "eval_samples_per_second": 562.167,
+      "eval_steps_per_second": 4.513,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.6e-05,
+      "loss": 0.1453,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7935779816513762,
+      "eval_loss": 0.5609800815582275,
+      "eval_runtime": 1.5514,
+      "eval_samples_per_second": 562.072,
+      "eval_steps_per_second": 4.512,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.1296,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.786697247706422,
+      "eval_loss": 0.645728349685669,
+      "eval_runtime": 1.5574,
+      "eval_samples_per_second": 559.892,
+      "eval_steps_per_second": 4.495,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "step": 3162,
+      "total_flos": 5.984501559302554e+16,
+      "train_loss": 0.20944157648056388,
+      "train_runtime": 2148.5153,
+      "train_samples_per_second": 1567.338,
+      "train_steps_per_second": 12.264
+    }
+  ],
+  "max_steps": 26350,
+  "num_train_epochs": 50,
+  "total_flos": 5.984501559302554e+16,
+  "trial_name": null,
+  "trial_params": null
+}