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 STSB
       type: glue
       config: stsb
       split: validation
@@ -28,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_new_pretrain_stsb
 
-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 STSB dataset.
 It achieves the following results on the evaluation set:
 - Loss: 11480.3916
 - Pearson: nan

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_combined_score": NaN,
+    "eval_loss": 11480.3916015625,
+    "eval_pearson": NaN,
+    "eval_runtime": 2.7241,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 550.648,
+    "eval_spearmanr": NaN,
+    "eval_steps_per_second": 4.405,
+    "train_loss": 11868.655555555555,
+    "train_runtime": 224.1308,
+    "train_samples": 5749,
+    "train_samples_per_second": 1282.51,
+    "train_steps_per_second": 10.039
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_combined_score": NaN,
+    "eval_loss": 11480.3916015625,
+    "eval_pearson": NaN,
+    "eval_runtime": 2.7241,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 550.648,
+    "eval_spearmanr": NaN,
+    "eval_steps_per_second": 4.405
+}

logs/events.out.tfevents.1685547798.serv-3318.2597307.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6379ae5ea0e396df0c29709f41fa4d1645efdd0079cd0fa028fea6de4326873f
+size 473

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 11868.655555555555,
+    "train_runtime": 224.1308,
+    "train_samples": 5749,
+    "train_samples_per_second": 1282.51,
+    "train_steps_per_second": 10.039
+}

trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 11480.3916015625,
+  "best_model_checkpoint": "hBERTv1_new_pretrain_stsb/checkpoint-45",
+  "epoch": 6.0,
+  "global_step": 270,
+  "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": 11870.5542,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 11480.3916015625,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.719,
+      "eval_samples_per_second": 551.676,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.413,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00048,
+      "loss": 11864.3806,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 11480.3916015625,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.7234,
+      "eval_samples_per_second": 550.777,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.406,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00047,
+      "loss": 11929.5181,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 11480.3916015625,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.7075,
+      "eval_samples_per_second": 554.009,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.432,
+      "step": 135
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00046,
+      "loss": 11830.7097,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 11480.3916015625,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.7221,
+      "eval_samples_per_second": 551.036,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.408,
+      "step": 180
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.00045000000000000004,
+      "loss": 11918.4542,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 11480.3916015625,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.7222,
+      "eval_samples_per_second": 551.02,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.408,
+      "step": 225
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00044,
+      "loss": 11798.3167,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 11480.3916015625,
+      "eval_pearson": NaN,
+      "eval_runtime": 2.7212,
+      "eval_samples_per_second": 551.221,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.41,
+      "step": 270
+    },
+    {
+      "epoch": 6.0,
+      "step": 270,
+      "total_flos": 5108409405800448.0,
+      "train_loss": 11868.655555555555,
+      "train_runtime": 224.1308,
+      "train_samples_per_second": 1282.51,
+      "train_steps_per_second": 10.039
+    }
+  ],
+  "max_steps": 2250,
+  "num_train_epochs": 50,
+  "total_flos": 5108409405800448.0,
+  "trial_name": null,
+  "trial_params": null
+}