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
@@ -24,7 +26,7 @@ model-index:
       value: 0.6838235294117647
     - name: F1
       type: f1
-      value: 0.7867768595041322
+      value: 0.7895595432300163
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv2_new_no_pretrain_mrpc
 
-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 MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1249
+- Loss: 0.5914
 - Accuracy: 0.6838
-- F1: 0.7868
-- Combined Score: 0.7353
+- F1: 0.7896
+- Combined Score: 0.7367
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 6.0,
+    "epoch": 7.0,
     "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6242262721061707,
-    "eval_runtime": 0.6905,
+    "eval_combined_score": 0.7366915363208906,
+    "eval_f1": 0.7895595432300163,
+    "eval_loss": 0.5914379358291626,
+    "eval_runtime": 1.8267,
     "eval_samples": 408,
-    "eval_samples_per_second": 590.877,
-    "eval_steps_per_second": 5.793,
-    "train_loss": 0.7478585407651704,
-    "train_runtime": 128.9129,
+    "eval_samples_per_second": 223.355,
+    "eval_steps_per_second": 2.19,
+    "train_loss": 0.42316288548737324,
+    "train_runtime": 454.4346,
     "train_samples": 3668,
-    "train_samples_per_second": 1422.666,
-    "train_steps_per_second": 11.248
+    "train_samples_per_second": 403.578,
+    "train_steps_per_second": 3.191
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 6.0,
+    "epoch": 7.0,
     "eval_accuracy": 0.6838235294117647,
-    "eval_combined_score": 0.7480253018237863,
-    "eval_f1": 0.8122270742358079,
-    "eval_loss": 0.6242262721061707,
-    "eval_runtime": 0.6905,
+    "eval_combined_score": 0.7366915363208906,
+    "eval_f1": 0.7895595432300163,
+    "eval_loss": 0.5914379358291626,
+    "eval_runtime": 1.8267,
     "eval_samples": 408,
-    "eval_samples_per_second": 590.877,
-    "eval_steps_per_second": 5.793
+    "eval_samples_per_second": 223.355,
+    "eval_steps_per_second": 2.19
 }

logs/events.out.tfevents.1686749324.garda.2589545.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaed7936e0110bc2b9b2f2339b944c8cff507c0e7c9d592aa1bbaf89194af206
+size 467

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 6.0,
-    "train_loss": 0.7478585407651704,
-    "train_runtime": 128.9129,
+    "epoch": 7.0,
+    "train_loss": 0.42316288548737324,
+    "train_runtime": 454.4346,
     "train_samples": 3668,
-    "train_samples_per_second": 1422.666,
-    "train_steps_per_second": 11.248
+    "train_samples_per_second": 403.578,
+    "train_steps_per_second": 3.191
 }

trainer_state.json

@@ -1,16 +1,16 @@
 {
-  "best_metric": 0.6242262721061707,
-  "best_model_checkpoint": "hBERTv2_new_no_pretrain_mrpc/checkpoint-29",
-  "epoch": 6.0,
-  "global_step": 174,
+  "best_metric": 0.5914379358291626,
+  "best_model_checkpoint": "hBERTv2_new_no_pretrain_mrpc/checkpoint-58",
+  "epoch": 7.0,
+  "global_step": 203,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 0.0004906896551724138,
-      "loss": 1.2542,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.6685,
       "step": 29
     },
     {
@@ -18,110 +18,127 @@
       "eval_accuracy": 0.6838235294117647,
       "eval_combined_score": 0.7480253018237863,
       "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6242262721061707,
-      "eval_runtime": 0.6879,
-      "eval_samples_per_second": 593.139,
-      "eval_steps_per_second": 5.815,
+      "eval_loss": 0.6107444167137146,
+      "eval_runtime": 1.8389,
+      "eval_samples_per_second": 221.872,
+      "eval_steps_per_second": 2.175,
       "step": 29
     },
     {
       "epoch": 2.0,
-      "learning_rate": 0.0004806896551724138,
-      "loss": 0.6656,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.6337,
       "step": 58
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6247109770774841,
-      "eval_runtime": 0.6908,
-      "eval_samples_per_second": 590.621,
-      "eval_steps_per_second": 5.79,
+      "eval_combined_score": 0.7366915363208906,
+      "eval_f1": 0.7895595432300163,
+      "eval_loss": 0.5914379358291626,
+      "eval_runtime": 1.8463,
+      "eval_samples_per_second": 220.985,
+      "eval_steps_per_second": 2.167,
       "step": 58
     },
     {
       "epoch": 3.0,
-      "learning_rate": 0.0004706896551724138,
-      "loss": 0.648,
+      "learning_rate": 3.76e-05,
+      "loss": 0.529,
       "step": 87
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6308785080909729,
-      "eval_runtime": 0.6926,
-      "eval_samples_per_second": 589.073,
-      "eval_steps_per_second": 5.775,
+      "eval_accuracy": 0.6642156862745098,
+      "eval_combined_score": 0.7173674746280421,
+      "eval_f1": 0.7705192629815745,
+      "eval_loss": 0.6385138034820557,
+      "eval_runtime": 1.8437,
+      "eval_samples_per_second": 221.293,
+      "eval_steps_per_second": 2.17,
       "step": 87
     },
     {
       "epoch": 4.0,
-      "learning_rate": 0.0004606896551724138,
-      "loss": 0.6448,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.4182,
       "step": 116
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6373123526573181,
-      "eval_runtime": 0.6915,
-      "eval_samples_per_second": 589.995,
-      "eval_steps_per_second": 5.784,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7518003635685653,
+      "eval_f1": 0.8050713153724247,
+      "eval_loss": 0.6618954539299011,
+      "eval_runtime": 1.8368,
+      "eval_samples_per_second": 222.12,
+      "eval_steps_per_second": 2.178,
       "step": 116
     },
     {
       "epoch": 5.0,
-      "learning_rate": 0.00045068965517241377,
-      "loss": 0.6423,
+      "learning_rate": 3.6e-05,
+      "loss": 0.3095,
       "step": 145
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6278728246688843,
-      "eval_runtime": 0.6904,
-      "eval_samples_per_second": 591.002,
-      "eval_steps_per_second": 5.794,
+      "eval_accuracy": 0.6470588235294118,
+      "eval_combined_score": 0.7019077901430844,
+      "eval_f1": 0.7567567567567568,
+      "eval_loss": 1.0039604902267456,
+      "eval_runtime": 1.8407,
+      "eval_samples_per_second": 221.66,
+      "eval_steps_per_second": 2.173,
       "step": 145
     },
     {
       "epoch": 6.0,
-      "learning_rate": 0.00044068965517241385,
-      "loss": 0.6323,
+      "learning_rate": 3.52e-05,
+      "loss": 0.2219,
       "step": 174
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6838235294117647,
-      "eval_combined_score": 0.7480253018237863,
-      "eval_f1": 0.8122270742358079,
-      "eval_loss": 0.6351138949394226,
-      "eval_runtime": 0.6918,
-      "eval_samples_per_second": 589.757,
-      "eval_steps_per_second": 5.782,
+      "eval_accuracy": 0.6225490196078431,
+      "eval_combined_score": 0.6659914909359972,
+      "eval_f1": 0.7094339622641511,
+      "eval_loss": 0.945849597454071,
+      "eval_runtime": 1.8381,
+      "eval_samples_per_second": 221.964,
+      "eval_steps_per_second": 2.176,
       "step": 174
     },
     {
-      "epoch": 6.0,
-      "step": 174,
-      "total_flos": 3220632565186560.0,
-      "train_loss": 0.7478585407651704,
-      "train_runtime": 128.9129,
-      "train_samples_per_second": 1422.666,
-      "train_steps_per_second": 11.248
+      "epoch": 7.0,
+      "learning_rate": 3.44e-05,
+      "loss": 0.1813,
+      "step": 203
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6838235294117647,
+      "eval_combined_score": 0.7353001944579485,
+      "eval_f1": 0.7867768595041322,
+      "eval_loss": 1.1248677968978882,
+      "eval_runtime": 1.8303,
+      "eval_samples_per_second": 222.913,
+      "eval_steps_per_second": 2.185,
+      "step": 203
+    },
+    {
+      "epoch": 7.0,
+      "step": 203,
+      "total_flos": 3757404659384320.0,
+      "train_loss": 0.42316288548737324,
+      "train_runtime": 454.4346,
+      "train_samples_per_second": 403.578,
+      "train_steps_per_second": 3.191
     }
   ],
   "max_steps": 1450,
   "num_train_epochs": 50,
-  "total_flos": 3220632565186560.0,
+  "total_flos": 3757404659384320.0,
   "trial_name": null,
   "trial_params": null
 }