End of training

README.md

@@ -1,11 +1,26 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: hBERTv2_data_aug_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5091743119266054
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,9 +28,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_data_aug_sst2
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on an unknown dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7191
+- Loss: 0.6962
 - Accuracy: 0.5092
 
 ## Model description

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5091743119266054,
+    "eval_loss": 0.6962016820907593,
+    "eval_runtime": 1.0318,
+    "eval_samples": 872,
+    "eval_samples_per_second": 845.134,
+    "eval_steps_per_second": 3.877,
+    "train_loss": 0.6858762312125425,
+    "train_runtime": 26730.9121,
+    "train_samples": 1119619,
+    "train_samples_per_second": 2094.24,
+    "train_steps_per_second": 8.182
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.5091743119266054,
+    "eval_loss": 0.6962016820907593,
+    "eval_runtime": 1.0318,
+    "eval_samples": 872,
+    "eval_samples_per_second": 845.134,
+    "eval_steps_per_second": 3.877
+}

logs/events.out.tfevents.1678020126.serv-3317.65033.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32be9e7ef99f99068416e975f72fece7e630bc4e448db7197d0f173d30bcb293
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "train_loss": 0.6858762312125425,
+    "train_runtime": 26730.9121,
+    "train_samples": 1119619,
+    "train_samples_per_second": 2094.24,
+    "train_steps_per_second": 8.182
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 0.6962016820907593,
+  "best_model_checkpoint": "hBERTv2_data_aug_sst2/checkpoint-8748",
+  "epoch": 7.0,
+  "global_step": 30618,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.900022862368542e-05,
+      "loss": 0.6879,
+      "step": 4374
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.699462890625,
+      "eval_runtime": 1.0182,
+      "eval_samples_per_second": 856.455,
+      "eval_steps_per_second": 3.929,
+      "step": 4374
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.800068587105625e-05,
+      "loss": 0.6873,
+      "step": 8748
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6962016820907593,
+      "eval_runtime": 1.0178,
+      "eval_samples_per_second": 856.766,
+      "eval_steps_per_second": 3.93,
+      "step": 8748
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.700114311842707e-05,
+      "loss": 0.6869,
+      "step": 13122
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.7094569802284241,
+      "eval_runtime": 1.0227,
+      "eval_samples_per_second": 852.631,
+      "eval_steps_per_second": 3.911,
+      "step": 13122
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.60016003657979e-05,
+      "loss": 0.6862,
+      "step": 17496
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.7039492726325989,
+      "eval_runtime": 1.0224,
+      "eval_samples_per_second": 852.927,
+      "eval_steps_per_second": 3.913,
+      "step": 17496
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.500182898948331e-05,
+      "loss": 0.685,
+      "step": 21870
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.7252029180526733,
+      "eval_runtime": 1.0198,
+      "eval_samples_per_second": 855.038,
+      "eval_steps_per_second": 3.922,
+      "step": 21870
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.400228623685414e-05,
+      "loss": 0.6841,
+      "step": 26244
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.7280449867248535,
+      "eval_runtime": 1.0258,
+      "eval_samples_per_second": 850.051,
+      "eval_steps_per_second": 3.899,
+      "step": 26244
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.300274348422496e-05,
+      "loss": 0.6837,
+      "step": 30618
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.7190725207328796,
+      "eval_runtime": 1.0384,
+      "eval_samples_per_second": 839.741,
+      "eval_steps_per_second": 3.852,
+      "step": 30618
+    },
+    {
+      "epoch": 7.0,
+      "step": 30618,
+      "total_flos": 9.761667383348429e+17,
+      "train_loss": 0.6858762312125425,
+      "train_runtime": 26730.9121,
+      "train_samples_per_second": 2094.24,
+      "train_steps_per_second": 8.182
+    }
+  ],
+  "max_steps": 218700,
+  "num_train_epochs": 50,
+  "total_flos": 9.761667383348429e+17,
+  "trial_name": null,
+  "trial_params": null
+}