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 MRPC
       type: glue
       config: mrpc
       split: validation
@@ -32,9 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_new_pretrain_mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 16.9510
+- Loss: 16.9467
 - Accuracy: 0.6838
 - F1: 0.8122
 - Combined Score: 0.7480

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 13.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 16.946691513061523,
+    "eval_runtime": 0.7508,
+    "eval_samples": 408,
+    "eval_samples_per_second": 543.443,
+    "eval_steps_per_second": 5.328,
+    "train_loss": 18.96294307961704,
+    "train_runtime": 317.3548,
+    "train_samples": 3668,
+    "train_samples_per_second": 577.902,
+    "train_steps_per_second": 4.569
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 13.0,
+    "eval_accuracy": 0.6838235294117647,
+    "eval_combined_score": 0.7480253018237863,
+    "eval_f1": 0.8122270742358079,
+    "eval_loss": 16.946691513061523,
+    "eval_runtime": 0.7508,
+    "eval_samples": 408,
+    "eval_samples_per_second": 543.443,
+    "eval_steps_per_second": 5.328
+}

logs/events.out.tfevents.1685531384.serv-3318.2597307.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced4a2a729bc434e2be32f842e0a96ce51c194e15857ec8745b07c2714d7da9d
+size 467

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 13.0,
+    "train_loss": 18.96294307961704,
+    "train_runtime": 317.3548,
+    "train_samples": 3668,
+    "train_samples_per_second": 577.902,
+    "train_steps_per_second": 4.569
+}

trainer_state.json

@@ -0,0 +1,246 @@
+{
+  "best_metric": 16.946691513061523,
+  "best_model_checkpoint": "hBERTv1_new_pretrain_mrpc/checkpoint-232",
+  "epoch": 13.0,
+  "global_step": 377,
+  "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": 19.6767,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.958946228027344,
+      "eval_runtime": 0.7573,
+      "eval_samples_per_second": 538.74,
+      "eval_steps_per_second": 5.282,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00048,
+      "loss": 19.3493,
+      "step": 58
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.958946228027344,
+      "eval_runtime": 0.7497,
+      "eval_samples_per_second": 544.244,
+      "eval_steps_per_second": 5.336,
+      "step": 58
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00047,
+      "loss": 19.2027,
+      "step": 87
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.960784912109375,
+      "eval_runtime": 0.751,
+      "eval_samples_per_second": 543.309,
+      "eval_steps_per_second": 5.327,
+      "step": 87
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00046,
+      "loss": 18.331,
+      "step": 116
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.952205657958984,
+      "eval_runtime": 0.7511,
+      "eval_samples_per_second": 543.213,
+      "eval_steps_per_second": 5.326,
+      "step": 116
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00045000000000000004,
+      "loss": 18.7621,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.96017074584961,
+      "eval_runtime": 0.7546,
+      "eval_samples_per_second": 540.675,
+      "eval_steps_per_second": 5.301,
+      "step": 145
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00044,
+      "loss": 18.947,
+      "step": 174
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.95649528503418,
+      "eval_runtime": 0.7509,
+      "eval_samples_per_second": 543.351,
+      "eval_steps_per_second": 5.327,
+      "step": 174
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00043,
+      "loss": 18.9881,
+      "step": 203
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.957107543945312,
+      "eval_runtime": 0.7504,
+      "eval_samples_per_second": 543.682,
+      "eval_steps_per_second": 5.33,
+      "step": 203
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.00042,
+      "loss": 19.398,
+      "step": 232
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.946691513061523,
+      "eval_runtime": 0.7513,
+      "eval_samples_per_second": 543.058,
+      "eval_steps_per_second": 5.324,
+      "step": 232
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.00041,
+      "loss": 18.4123,
+      "step": 261
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.950366973876953,
+      "eval_runtime": 0.7508,
+      "eval_samples_per_second": 543.454,
+      "eval_steps_per_second": 5.328,
+      "step": 261
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0004,
+      "loss": 18.3449,
+      "step": 290
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.953432083129883,
+      "eval_runtime": 0.7521,
+      "eval_samples_per_second": 542.492,
+      "eval_steps_per_second": 5.319,
+      "step": 290
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00039000000000000005,
+      "loss": 18.9622,
+      "step": 319
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.95159339904785,
+      "eval_runtime": 0.7537,
+      "eval_samples_per_second": 541.334,
+      "eval_steps_per_second": 5.307,
+      "step": 319
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.00038,
+      "loss": 19.1266,
+      "step": 348
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.95159339904785,
+      "eval_runtime": 0.7515,
+      "eval_samples_per_second": 542.931,
+      "eval_steps_per_second": 5.323,
+      "step": 348
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 0.00037,
+      "loss": 19.0174,
+      "step": 377
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7480253018237863,
+      "eval_f1": 0.8122270742358079,
+      "eval_loss": 16.95098114013672,
+      "eval_runtime": 0.7516,
+      "eval_samples_per_second": 542.838,
+      "eval_steps_per_second": 5.322,
+      "step": 377
+    },
+    {
+      "epoch": 13.0,
+      "step": 377,
+      "total_flos": 7061846666248192.0,
+      "train_loss": 18.96294307961704,
+      "train_runtime": 317.3548,
+      "train_samples_per_second": 577.902,
+      "train_steps_per_second": 4.569
+    }
+  ],
+  "max_steps": 1450,
+  "num_train_epochs": 50,
+  "total_flos": 7061846666248192.0,
+  "trial_name": null,
+  "trial_params": null
+}