End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- en
 tags:
 - generated_from_trainer
 datasets:
@@ -13,7 +15,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: glue
+      name: GLUE QQP
       type: glue
       config: qqp
       split: validation
@@ -32,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_no_pretrain_qqp
 
-This model is a fine-tuned version of [](https://huggingface.co/) on the glue dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 0.6598
 - Accuracy: 0.6318
 - F1: 0.0
 - Combined Score: 0.3159

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6318327974276527,
+    "eval_combined_score": 0.3159163987138264,
+    "eval_f1": 0.0,
+    "eval_loss": 0.6598194241523743,
+    "eval_runtime": 70.3817,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 574.439,
+    "eval_steps_per_second": 4.49,
+    "train_loss": 0.4408971084521376,
+    "train_runtime": 11254.1141,
+    "train_samples": 363846,
+    "train_samples_per_second": 1616.502,
+    "train_steps_per_second": 12.631
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6318327974276527,
+    "eval_combined_score": 0.3159163987138264,
+    "eval_f1": 0.0,
+    "eval_loss": 0.6598194241523743,
+    "eval_runtime": 70.3817,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 574.439,
+    "eval_steps_per_second": 4.49
+}

logs/events.out.tfevents.1685355917.serv-9225.2840720.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac796d6b7588c62d266f9f1ee44ef85c74f43b964dca27e9725f8baa72fb0530
+size 475

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.4408971084521376,
+    "train_runtime": 11254.1141,
+    "train_samples": 363846,
+    "train_samples_per_second": 1616.502,
+    "train_steps_per_second": 12.631
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.6598194241523743,
+  "best_model_checkpoint": "hBERTv1_no_pretrain_qqp/checkpoint-2843",
+  "epoch": 6.0,
+  "global_step": 17058,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0004900070348223708,
+      "loss": 0.6693,
+      "step": 2843
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6598194241523743,
+      "eval_runtime": 70.7024,
+      "eval_samples_per_second": 571.833,
+      "eval_steps_per_second": 4.469,
+      "step": 2843
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00048050650721069294,
+      "loss": 0.6591,
+      "step": 5686
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 70.3827,
+      "eval_samples_per_second": 574.431,
+      "eval_steps_per_second": 4.49,
+      "step": 5686
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00047059092507914177,
+      "loss": 0.6588,
+      "step": 8529
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 70.6601,
+      "eval_samples_per_second": 572.176,
+      "eval_steps_per_second": 4.472,
+      "step": 8529
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00046059092507914174,
+      "loss": 0.6582,
+      "step": 11372
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 69.7585,
+      "eval_samples_per_second": 579.571,
+      "eval_steps_per_second": 4.53,
+      "step": 11372
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0004505909250791417,
+      "loss": 0.0,
+      "step": 14215
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 69.723,
+      "eval_samples_per_second": 579.866,
+      "eval_steps_per_second": 4.532,
+      "step": 14215
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0004405909250791418,
+      "loss": 0.0,
+      "step": 17058
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6318327974276527,
+      "eval_combined_score": 0.3159163987138264,
+      "eval_f1": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 69.5815,
+      "eval_samples_per_second": 581.045,
+      "eval_steps_per_second": 4.541,
+      "step": 17058
+    },
+    {
+      "epoch": 6.0,
+      "step": 17058,
+      "total_flos": 3.2330651506468454e+17,
+      "train_loss": 0.4408971084521376,
+      "train_runtime": 11254.1141,
+      "train_samples_per_second": 1616.502,
+      "train_steps_per_second": 12.631
+    }
+  ],
+  "max_steps": 142150,
+  "num_train_epochs": 50,
+  "total_flos": 3.2330651506468454e+17,
+  "trial_name": null,
+  "trial_params": null
+}