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 SST2
       type: glue
       config: sst2
       split: validation
@@ -28,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # add_BERT_no_pretrain_sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7002
+- Loss: 0.6936
 - Accuracy: 0.5092
 
 ## Model description

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 6.0,
     "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6978054046630859,
-    "eval_runtime": 1.3601,
+    "eval_loss": 0.6935691237449646,
+    "eval_runtime": 1.6342,
     "eval_samples": 872,
-    "eval_samples_per_second": 641.11,
-    "eval_steps_per_second": 5.147,
-    "train_loss": 0.5792089338019104,
-    "train_runtime": 1859.6741,
+    "eval_samples_per_second": 533.578,
+    "eval_steps_per_second": 4.283,
+    "train_loss": 0.6896291946324271,
+    "train_runtime": 2408.1345,
     "train_samples": 67349,
-    "train_samples_per_second": 1810.774,
-    "train_steps_per_second": 14.169
+    "train_samples_per_second": 1398.365,
+    "train_steps_per_second": 10.942
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 6.0,
     "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6978054046630859,
-    "eval_runtime": 1.3601,
+    "eval_loss": 0.6935691237449646,
+    "eval_runtime": 1.6342,
     "eval_samples": 872,
-    "eval_samples_per_second": 641.11,
-    "eval_steps_per_second": 5.147
+    "eval_samples_per_second": 533.578,
+    "eval_steps_per_second": 4.283
 }

logs/events.out.tfevents.1686775817.serv-9219.1715196.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a971aa113d8472d020e6c941559f2116a1c6116583dbedbb69fc71c2744e2b8
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 6.0,
-    "train_loss": 0.5792089338019104,
-    "train_runtime": 1859.6741,
+    "train_loss": 0.6896291946324271,
+    "train_runtime": 2408.1345,
     "train_samples": 67349,
-    "train_samples_per_second": 1810.774,
-    "train_steps_per_second": 14.169
+    "train_samples_per_second": 1398.365,
+    "train_steps_per_second": 10.942
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6978054046630859,
+  "best_metric": 0.6935691237449646,
   "best_model_checkpoint": "add_BERT_no_pretrain_sst2/checkpoint-527",
   "epoch": 6.0,
   "global_step": 3162,
@@ -9,102 +9,102 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 0.0004900379506641366,
-      "loss": 0.7276,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 0.6983,
       "step": 527
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6978054046630859,
-      "eval_runtime": 1.3727,
-      "eval_samples_per_second": 635.255,
-      "eval_steps_per_second": 5.1,
+      "eval_loss": 0.6935691237449646,
+      "eval_runtime": 1.6343,
+      "eval_samples_per_second": 533.567,
+      "eval_steps_per_second": 4.283,
       "step": 527
     },
     {
       "epoch": 2.0,
-      "learning_rate": 0.00048003795066413666,
-      "loss": 0.6872,
+      "learning_rate": 3.8400000000000005e-05,
+      "loss": 0.6895,
       "step": 1054
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.7013314366340637,
-      "eval_runtime": 1.3699,
-      "eval_samples_per_second": 636.538,
-      "eval_steps_per_second": 5.11,
+      "eval_loss": 0.7089212536811829,
+      "eval_runtime": 1.6328,
+      "eval_samples_per_second": 534.054,
+      "eval_steps_per_second": 4.287,
       "step": 1054
     },
     {
       "epoch": 3.0,
-      "learning_rate": 0.00047003795066413663,
-      "loss": 0.6873,
+      "learning_rate": 3.76e-05,
+      "loss": 0.6881,
       "step": 1581
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6995900273323059,
-      "eval_runtime": 1.3659,
-      "eval_samples_per_second": 638.425,
-      "eval_steps_per_second": 5.125,
+      "eval_loss": 0.6993499994277954,
+      "eval_runtime": 1.6457,
+      "eval_samples_per_second": 529.872,
+      "eval_steps_per_second": 4.254,
       "step": 1581
     },
     {
       "epoch": 4.0,
-      "learning_rate": 0.0004604554079696395,
-      "loss": 0.6868,
+      "learning_rate": 3.680000000000001e-05,
+      "loss": 0.6875,
       "step": 2108
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.4908256880733945,
-      "eval_loss": NaN,
-      "eval_runtime": 1.3643,
-      "eval_samples_per_second": 639.154,
-      "eval_steps_per_second": 5.131,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.6993725299835205,
+      "eval_runtime": 1.6446,
+      "eval_samples_per_second": 530.225,
+      "eval_steps_per_second": 4.256,
       "step": 2108
     },
     {
       "epoch": 5.0,
-      "learning_rate": 0.000453168880455408,
-      "loss": 0.6864,
+      "learning_rate": 3.6e-05,
+      "loss": 0.6874,
       "step": 2635
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.4908256880733945,
-      "eval_loss": NaN,
-      "eval_runtime": 1.3451,
-      "eval_samples_per_second": 648.288,
-      "eval_steps_per_second": 5.204,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.694109320640564,
+      "eval_runtime": 1.638,
+      "eval_samples_per_second": 532.346,
+      "eval_steps_per_second": 4.273,
       "step": 2635
     },
     {
       "epoch": 6.0,
-      "learning_rate": 0.000443168880455408,
-      "loss": 0.0,
+      "learning_rate": 3.52e-05,
+      "loss": 0.687,
       "step": 3162
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.4908256880733945,
-      "eval_loss": NaN,
-      "eval_runtime": 1.3487,
-      "eval_samples_per_second": 646.555,
-      "eval_steps_per_second": 5.19,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 0.7002017498016357,
+      "eval_runtime": 1.6315,
+      "eval_samples_per_second": 534.473,
+      "eval_steps_per_second": 4.29,
       "step": 3162
     },
     {
       "epoch": 6.0,
       "step": 3162,
       "total_flos": 5.771431023476736e+16,
-      "train_loss": 0.5792089338019104,
-      "train_runtime": 1859.6741,
-      "train_samples_per_second": 1810.774,
-      "train_steps_per_second": 14.169
+      "train_loss": 0.6896291946324271,
+      "train_runtime": 2408.1345,
+      "train_samples_per_second": 1398.365,
+      "train_steps_per_second": 10.942
     }
   ],
   "max_steps": 26350,