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 RTE
       type: glue
       config: rte
       split: validation
@@ -28,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_new_pretrain_rte
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new) on the glue dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new) on the GLUE RTE dataset.
 It achieves the following results on the evaluation set:
 - Loss: 28.2681
 - Accuracy: 0.4729

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.4729241877256318,
+    "eval_loss": 28.268051147460938,
+    "eval_runtime": 0.5114,
+    "eval_samples": 277,
+    "eval_samples_per_second": 541.669,
+    "eval_steps_per_second": 5.866,
+    "train_loss": 29.028575642903647,
+    "train_runtime": 102.0364,
+    "train_samples": 2490,
+    "train_samples_per_second": 1220.153,
+    "train_steps_per_second": 9.8
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.4729241877256318,
+    "eval_loss": 28.268051147460938,
+    "eval_runtime": 0.5114,
+    "eval_samples": 277,
+    "eval_samples_per_second": 541.669,
+    "eval_steps_per_second": 5.866
+}

logs/events.out.tfevents.1685547527.serv-3318.2597307.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf02ac44f3aa6d7ff81a7e86fe6843799a11293c03fcce22a91ae69337a6ea0
+size 357

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 29.028575642903647,
+    "train_runtime": 102.0364,
+    "train_samples": 2490,
+    "train_samples_per_second": 1220.153,
+    "train_steps_per_second": 9.8
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 28.268051147460938,
+  "best_model_checkpoint": "hBERTv1_new_pretrain_rte/checkpoint-20",
+  "epoch": 6.0,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00049,
+      "loss": 28.8034,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 28.268051147460938,
+      "eval_runtime": 0.5081,
+      "eval_samples_per_second": 545.128,
+      "eval_steps_per_second": 5.904,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00048,
+      "loss": 28.8444,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 28.268051147460938,
+      "eval_runtime": 0.5097,
+      "eval_samples_per_second": 543.476,
+      "eval_steps_per_second": 5.886,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00047,
+      "loss": 28.6738,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 28.268051147460938,
+      "eval_runtime": 0.5098,
+      "eval_samples_per_second": 543.347,
+      "eval_steps_per_second": 5.885,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00046,
+      "loss": 29.3662,
+      "step": 80
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 28.268051147460938,
+      "eval_runtime": 0.5103,
+      "eval_samples_per_second": 542.814,
+      "eval_steps_per_second": 5.879,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00045000000000000004,
+      "loss": 30.0413,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 28.268051147460938,
+      "eval_runtime": 0.5111,
+      "eval_samples_per_second": 541.935,
+      "eval_steps_per_second": 5.869,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00044,
+      "loss": 28.4423,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 28.268051147460938,
+      "eval_runtime": 0.5109,
+      "eval_samples_per_second": 542.142,
+      "eval_steps_per_second": 5.872,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "step": 120,
+      "total_flos": 2212565757198336.0,
+      "train_loss": 29.028575642903647,
+      "train_runtime": 102.0364,
+      "train_samples_per_second": 1220.153,
+      "train_steps_per_second": 9.8
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 50,
+  "total_flos": 2212565757198336.0,
+  "trial_name": null,
+  "trial_params": null
+}