End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_100_v1_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.805045871559633
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_100_v1_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6460
-- Accuracy: 0.8096
+- Loss: 0.4466
+- Accuracy: 0.8050
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 9.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6954379081726074,
-    "eval_runtime": 0.2621,
+    "epoch": 6.0,
+    "eval_accuracy": 0.805045871559633,
+    "eval_loss": 0.4466005265712738,
+    "eval_runtime": 0.2786,
     "eval_samples": 872,
-    "eval_samples_per_second": 3326.351,
-    "eval_steps_per_second": 15.258,
-    "total_flos": 1.5895185860385792e+16,
-    "train_loss": 0.6873250633779199,
-    "train_runtime": 324.1575,
+    "eval_samples_per_second": 3130.287,
+    "eval_steps_per_second": 14.359,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.21827046196870128,
+    "train_runtime": 225.56,
     "train_samples": 67349,
-    "train_samples_per_second": 10388.315,
-    "train_steps_per_second": 40.721
+    "train_samples_per_second": 14929.289,
+    "train_steps_per_second": 58.521
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6954379081726074,
-    "eval_runtime": 0.2621,
+    "epoch": 6.0,
+    "eval_accuracy": 0.805045871559633,
+    "eval_loss": 0.4466005265712738,
+    "eval_runtime": 0.2786,
     "eval_samples": 872,
-    "eval_samples_per_second": 3326.351,
-    "eval_steps_per_second": 15.258
+    "eval_samples_per_second": 3130.287,
+    "eval_steps_per_second": 14.359
 }

logs/events.out.tfevents.1733327293.ki-g0008.1208741.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507d136c425b1c061096c3a4128514b97cc5871118f07e1af01b1380a2a5fb91
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 9.0,
-    "total_flos": 1.5895185860385792e+16,
-    "train_loss": 0.6873250633779199,
-    "train_runtime": 324.1575,
+    "epoch": 6.0,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.21827046196870128,
+    "train_runtime": 225.56,
     "train_samples": 67349,
-    "train_samples_per_second": 10388.315,
-    "train_steps_per_second": 40.721
+    "train_samples_per_second": 14929.289,
+    "train_steps_per_second": 58.521
 }

trainer_state.json

@@ -1,165 +1,117 @@
 {
-  "best_metric": 0.6954379081726074,
-  "best_model_checkpoint": "bert_tiny_lda_100_v1_sst2/checkpoint-1056",
-  "epoch": 9.0,
+  "best_metric": 0.4466005265712738,
+  "best_model_checkpoint": "bert_tiny_lda_100_v1_sst2/checkpoint-264",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 2376,
+  "global_step": 1584,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.3844283819198608,
-      "learning_rate": 0.00098,
-      "loss": 0.6923,
+      "grad_norm": 10.585709571838379,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4292,
       "step": 264
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6971402168273926,
-      "eval_runtime": 0.2617,
-      "eval_samples_per_second": 3332.644,
-      "eval_steps_per_second": 15.287,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 0.4466005265712738,
+      "eval_runtime": 0.2781,
+      "eval_samples_per_second": 3135.372,
+      "eval_steps_per_second": 14.382,
       "step": 264
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.17217020690441132,
-      "learning_rate": 0.00096,
-      "loss": 0.6871,
+      "grad_norm": 6.0157647132873535,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2589,
       "step": 528
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.700759768486023,
-      "eval_runtime": 0.271,
-      "eval_samples_per_second": 3217.292,
-      "eval_steps_per_second": 14.758,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 0.4592009484767914,
+      "eval_runtime": 0.2832,
+      "eval_samples_per_second": 3079.044,
+      "eval_steps_per_second": 14.124,
       "step": 528
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.30297428369522095,
-      "learning_rate": 0.00094,
-      "loss": 0.6868,
+      "grad_norm": 4.999380111694336,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2007,
       "step": 792
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6972835659980774,
-      "eval_runtime": 0.2641,
-      "eval_samples_per_second": 3301.314,
-      "eval_steps_per_second": 15.144,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 0.4953426420688629,
+      "eval_runtime": 0.2791,
+      "eval_samples_per_second": 3124.457,
+      "eval_steps_per_second": 14.332,
       "step": 792
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.40916410088539124,
-      "learning_rate": 0.00092,
-      "loss": 0.6868,
+      "grad_norm": 6.423249244689941,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1652,
       "step": 1056
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6954379081726074,
-      "eval_runtime": 0.2711,
-      "eval_samples_per_second": 3216.861,
-      "eval_steps_per_second": 14.756,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 0.5380478501319885,
+      "eval_runtime": 0.2813,
+      "eval_samples_per_second": 3099.753,
+      "eval_steps_per_second": 14.219,
       "step": 1056
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.10967253148555756,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6867,
+      "grad_norm": 4.089705467224121,
+      "learning_rate": 4.5e-05,
+      "loss": 0.137,
       "step": 1320
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6955096125602722,
-      "eval_runtime": 0.3123,
-      "eval_samples_per_second": 2791.787,
-      "eval_steps_per_second": 12.806,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 0.5538350939750671,
+      "eval_runtime": 0.2751,
+      "eval_samples_per_second": 3169.498,
+      "eval_steps_per_second": 14.539,
       "step": 1320
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.08872182667255402,
-      "learning_rate": 0.00088,
-      "loss": 0.6866,
+      "grad_norm": 6.120477199554443,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1185,
       "step": 1584
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6971402168273926,
-      "eval_runtime": 0.2648,
-      "eval_samples_per_second": 3292.65,
-      "eval_steps_per_second": 15.104,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 0.6460174918174744,
+      "eval_runtime": 0.2755,
+      "eval_samples_per_second": 3164.776,
+      "eval_steps_per_second": 14.517,
       "step": 1584
     },
     {
-      "epoch": 7.0,
-      "grad_norm": 0.1451181173324585,
-      "learning_rate": 0.00086,
-      "loss": 0.6865,
-      "step": 1848
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.698842465877533,
-      "eval_runtime": 0.2611,
-      "eval_samples_per_second": 3339.088,
-      "eval_steps_per_second": 15.317,
-      "step": 1848
-    },
-    {
-      "epoch": 8.0,
-      "grad_norm": 0.049795445054769516,
-      "learning_rate": 0.00084,
-      "loss": 0.6865,
-      "step": 2112
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6989858150482178,
-      "eval_runtime": 0.2626,
-      "eval_samples_per_second": 3320.526,
-      "eval_steps_per_second": 15.232,
-      "step": 2112
-    },
-    {
-      "epoch": 9.0,
-      "grad_norm": 0.18644928932189941,
-      "learning_rate": 0.00082,
-      "loss": 0.6866,
-      "step": 2376
-    },
-    {
-      "epoch": 9.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6969968676567078,
-      "eval_runtime": 0.2637,
-      "eval_samples_per_second": 3306.531,
-      "eval_steps_per_second": 15.168,
-      "step": 2376
-    },
-    {
-      "epoch": 9.0,
-      "step": 2376,
-      "total_flos": 1.5895185860385792e+16,
-      "train_loss": 0.6873250633779199,
-      "train_runtime": 324.1575,
-      "train_samples_per_second": 10388.315,
-      "train_steps_per_second": 40.721
+      "epoch": 6.0,
+      "step": 1584,
+      "total_flos": 1.0596790573590528e+16,
+      "train_loss": 0.21827046196870128,
+      "train_runtime": 225.56,
+      "train_samples_per_second": 14929.289,
+      "train_steps_per_second": 58.521
     }
   ],
   "logging_steps": 1,
@@ -188,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5895185860385792e+16,
+  "total_flos": 1.0596790573590528e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null