End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: bert_tiny_lda_20_v1_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,11 +34,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_20_v1_cola
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7010
-- Matthews Correlation: 0.0997
-- Accuracy: 0.6663
+- Loss: 0.6166
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 7.0,
+    "epoch": 6.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6171612739562988,
+    "eval_loss": 0.6166013479232788,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.3409,
+    "eval_runtime": 0.3287,
     "eval_samples": 1043,
-    "eval_samples_per_second": 3059.932,
-    "eval_steps_per_second": 14.669,
-    "total_flos": 1569664715049984.0,
-    "train_loss": 0.6148051734731979,
-    "train_runtime": 39.8995,
+    "eval_samples_per_second": 3172.795,
+    "eval_steps_per_second": 15.21,
+    "total_flos": 1345426898614272.0,
+    "train_loss": 0.5626457438749426,
+    "train_runtime": 34.5159,
     "train_samples": 8551,
-    "train_samples_per_second": 10715.664,
-    "train_steps_per_second": 42.607
+    "train_samples_per_second": 12387.04,
+    "train_steps_per_second": 49.253
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
-    "epoch": 7.0,
+    "epoch": 6.0,
     "eval_accuracy": 0.6912751793861389,
-    "eval_loss": 0.6171612739562988,
+    "eval_loss": 0.6166013479232788,
     "eval_matthews_correlation": 0.0,
-    "eval_runtime": 0.3409,
+    "eval_runtime": 0.3287,
     "eval_samples": 1043,
-    "eval_samples_per_second": 3059.932,
-    "eval_steps_per_second": 14.669
+    "eval_samples_per_second": 3172.795,
+    "eval_steps_per_second": 15.21
 }

logs/events.out.tfevents.1733323214.ki-g0008.1207389.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015c7501b84e7739b5dcef3e0a5b923266475bb9ebdf5857115d4ec601f0d4ed
+size 475

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 7.0,
-    "total_flos": 1569664715049984.0,
-    "train_loss": 0.6148051734731979,
-    "train_runtime": 39.8995,
+    "epoch": 6.0,
+    "total_flos": 1345426898614272.0,
+    "train_loss": 0.5626457438749426,
+    "train_runtime": 34.5159,
     "train_samples": 8551,
-    "train_samples_per_second": 10715.664,
-    "train_steps_per_second": 42.607
+    "train_samples_per_second": 12387.04,
+    "train_steps_per_second": 49.253
 }

trainer_state.json

@@ -1,140 +1,123 @@
 {
-  "best_metric": 0.6171612739562988,
-  "best_model_checkpoint": "bert_tiny_lda_20_v1_cola/checkpoint-68",
-  "epoch": 7.0,
+  "best_metric": 0.6166013479232788,
+  "best_model_checkpoint": "bert_tiny_lda_20_v1_cola/checkpoint-34",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 238,
+  "global_step": 204,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.6482819318771362,
-      "learning_rate": 0.00098,
-      "loss": 0.644,
+      "grad_norm": 0.6939840912818909,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6144,
       "step": 34
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6200581789016724,
+      "eval_loss": 0.6166013479232788,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3389,
-      "eval_samples_per_second": 3077.24,
-      "eval_steps_per_second": 14.752,
+      "eval_runtime": 0.33,
+      "eval_samples_per_second": 3160.493,
+      "eval_steps_per_second": 15.151,
       "step": 34
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.6033520698547363,
-      "learning_rate": 0.00096,
-      "loss": 0.6095,
+      "grad_norm": 0.7518705129623413,
+      "learning_rate": 4.8e-05,
+      "loss": 0.605,
       "step": 68
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6171612739562988,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3427,
-      "eval_samples_per_second": 3043.499,
-      "eval_steps_per_second": 14.59,
+      "eval_accuracy": 0.690316379070282,
+      "eval_loss": 0.6190095543861389,
+      "eval_matthews_correlation": 0.021324732257988185,
+      "eval_runtime": 0.3288,
+      "eval_samples_per_second": 3171.799,
+      "eval_steps_per_second": 15.205,
       "step": 68
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.1314589977264404,
-      "learning_rate": 0.00094,
-      "loss": 0.61,
+      "grad_norm": 1.1874852180480957,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5934,
       "step": 102
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6225749850273132,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3285,
-      "eval_samples_per_second": 3174.738,
-      "eval_steps_per_second": 15.219,
+      "eval_accuracy": 0.6759347915649414,
+      "eval_loss": 0.6171125769615173,
+      "eval_matthews_correlation": 0.0042962058184623795,
+      "eval_runtime": 0.3273,
+      "eval_samples_per_second": 3186.859,
+      "eval_steps_per_second": 15.277,
       "step": 102
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.43728774785995483,
-      "learning_rate": 0.00092,
-      "loss": 0.6103,
+      "grad_norm": 2.0468008518218994,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.567,
       "step": 136
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6193765997886658,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3288,
-      "eval_samples_per_second": 3171.974,
-      "eval_steps_per_second": 15.206,
+      "eval_accuracy": 0.6836050152778625,
+      "eval_loss": 0.6515802145004272,
+      "eval_matthews_correlation": 0.0362040039690685,
+      "eval_runtime": 0.3349,
+      "eval_samples_per_second": 3114.765,
+      "eval_steps_per_second": 14.932,
       "step": 136
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.6182149052619934,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6102,
+      "grad_norm": 1.4145721197128296,
+      "learning_rate": 4.5e-05,
+      "loss": 0.518,
       "step": 170
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6184196472167969,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3413,
-      "eval_samples_per_second": 3056.165,
-      "eval_steps_per_second": 14.651,
+      "eval_accuracy": 0.6692233681678772,
+      "eval_loss": 0.6388905048370361,
+      "eval_matthews_correlation": 0.06753595230469586,
+      "eval_runtime": 0.3341,
+      "eval_samples_per_second": 3121.766,
+      "eval_steps_per_second": 14.965,
       "step": 170
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.44735267758369446,
-      "learning_rate": 0.00088,
-      "loss": 0.6093,
+      "grad_norm": 2.289504289627075,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4781,
       "step": 204
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6192249059677124,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3321,
-      "eval_samples_per_second": 3140.303,
-      "eval_steps_per_second": 15.054,
+      "eval_accuracy": 0.666347086429596,
+      "eval_loss": 0.7010326981544495,
+      "eval_matthews_correlation": 0.0996916869431609,
+      "eval_runtime": 0.3437,
+      "eval_samples_per_second": 3034.449,
+      "eval_steps_per_second": 14.547,
       "step": 204
     },
     {
-      "epoch": 7.0,
-      "grad_norm": 1.2275654077529907,
-      "learning_rate": 0.00086,
-      "loss": 0.6103,
-      "step": 238
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.6912751793861389,
-      "eval_loss": 0.6196780800819397,
-      "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.3317,
-      "eval_samples_per_second": 3144.208,
-      "eval_steps_per_second": 15.073,
-      "step": 238
-    },
-    {
-      "epoch": 7.0,
-      "step": 238,
-      "total_flos": 1569664715049984.0,
-      "train_loss": 0.6148051734731979,
-      "train_runtime": 39.8995,
-      "train_samples_per_second": 10715.664,
-      "train_steps_per_second": 42.607
+      "epoch": 6.0,
+      "step": 204,
+      "total_flos": 1345426898614272.0,
+      "train_loss": 0.5626457438749426,
+      "train_runtime": 34.5159,
+      "train_samples_per_second": 12387.04,
+      "train_steps_per_second": 49.253
     }
   ],
   "logging_steps": 1,
@@ -163,7 +146,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1569664715049984.0,
+  "total_flos": 1345426898614272.0,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null