End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_5_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: 0.8153669724770642
 ---
 
 <!-- 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_5_v1_sst2
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_5_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_5_v1) on the GLUE SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6731
-- Accuracy: 0.7936
+- Loss: 0.4397
+- Accuracy: 0.8154
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
-    "epoch": 7.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6927546262741089,
-    "eval_runtime": 0.2812,
+    "epoch": 6.0,
+    "eval_accuracy": 0.8153669724770642,
+    "eval_loss": 0.4396927058696747,
+    "eval_runtime": 0.2696,
     "eval_samples": 872,
-    "eval_samples_per_second": 3101.546,
-    "eval_steps_per_second": 14.227,
-    "total_flos": 1.2362922335855616e+16,
-    "train_loss": 0.6844654330959568,
-    "train_runtime": 261.6721,
+    "eval_samples_per_second": 3234.929,
+    "eval_steps_per_second": 14.839,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.19634188305247913,
+    "train_runtime": 225.2591,
     "train_samples": 67349,
-    "train_samples_per_second": 12868.97,
-    "train_steps_per_second": 50.445
+    "train_samples_per_second": 14949.233,
+    "train_steps_per_second": 58.599
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 7.0,
-    "eval_accuracy": 0.5091743119266054,
-    "eval_loss": 0.6927546262741089,
-    "eval_runtime": 0.2812,
+    "epoch": 6.0,
+    "eval_accuracy": 0.8153669724770642,
+    "eval_loss": 0.4396927058696747,
+    "eval_runtime": 0.2696,
     "eval_samples": 872,
-    "eval_samples_per_second": 3101.546,
-    "eval_steps_per_second": 14.227
+    "eval_samples_per_second": 3234.929,
+    "eval_steps_per_second": 14.839
 }

logs/events.out.tfevents.1733325107.ki-g0008.1206925.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7a7425ee3ca1b3eff723f00ada33b6915463f7ed92b903284ada8628210280
+size 411

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 7.0,
-    "total_flos": 1.2362922335855616e+16,
-    "train_loss": 0.6844654330959568,
-    "train_runtime": 261.6721,
+    "epoch": 6.0,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.19634188305247913,
+    "train_runtime": 225.2591,
     "train_samples": 67349,
-    "train_samples_per_second": 12868.97,
-    "train_steps_per_second": 50.445
+    "train_samples_per_second": 14949.233,
+    "train_steps_per_second": 58.599
 }

trainer_state.json

@@ -1,133 +1,117 @@
 {
-  "best_metric": 0.6927546262741089,
-  "best_model_checkpoint": "bert_tiny_lda_5_v1_sst2/checkpoint-528",
-  "epoch": 7.0,
+  "best_metric": 0.4396927058696747,
+  "best_model_checkpoint": "bert_tiny_lda_5_v1_sst2/checkpoint-264",
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 1848,
+  "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": 1.4769257307052612,
-      "learning_rate": 0.00098,
-      "loss": 0.6805,
+      "grad_norm": 9.570955276489258,
+      "learning_rate": 4.9e-05,
+      "loss": 0.402,
       "step": 264
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.533256880733945,
-      "eval_loss": 0.694188117980957,
-      "eval_runtime": 0.2722,
-      "eval_samples_per_second": 3203.363,
-      "eval_steps_per_second": 14.694,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 0.4396927058696747,
+      "eval_runtime": 0.2768,
+      "eval_samples_per_second": 3150.401,
+      "eval_steps_per_second": 14.451,
       "step": 264
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.41901111602783203,
-      "learning_rate": 0.00096,
-      "loss": 0.6795,
+      "grad_norm": 10.17089557647705,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2385,
       "step": 528
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6927546262741089,
-      "eval_runtime": 0.2751,
-      "eval_samples_per_second": 3169.792,
-      "eval_steps_per_second": 14.54,
+      "eval_accuracy": 0.8038990825688074,
+      "eval_loss": 0.49887505173683167,
+      "eval_runtime": 0.2789,
+      "eval_samples_per_second": 3126.276,
+      "eval_steps_per_second": 14.341,
       "step": 528
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.19532398879528046,
-      "learning_rate": 0.00094,
-      "loss": 0.6848,
+      "grad_norm": 6.174217224121094,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1813,
       "step": 792
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6971402168273926,
-      "eval_runtime": 0.2751,
-      "eval_samples_per_second": 3169.886,
-      "eval_steps_per_second": 14.541,
+      "eval_accuracy": 0.7970183486238532,
+      "eval_loss": 0.5259420871734619,
+      "eval_runtime": 0.2888,
+      "eval_samples_per_second": 3019.151,
+      "eval_steps_per_second": 13.849,
       "step": 792
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.3345678448677063,
-      "learning_rate": 0.00092,
-      "loss": 0.6868,
+      "grad_norm": 6.113431930541992,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1449,
       "step": 1056
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.695724606513977,
-      "eval_runtime": 0.2812,
-      "eval_samples_per_second": 3101.48,
-      "eval_steps_per_second": 14.227,
+      "eval_accuracy": 0.8004587155963303,
+      "eval_loss": 0.5909135341644287,
+      "eval_runtime": 0.2819,
+      "eval_samples_per_second": 3093.767,
+      "eval_steps_per_second": 14.192,
       "step": 1056
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.1190953329205513,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 0.6866,
+      "grad_norm": 3.880650043487549,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1159,
       "step": 1320
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6954379081726074,
-      "eval_runtime": 0.2865,
-      "eval_samples_per_second": 3043.347,
-      "eval_steps_per_second": 13.96,
+      "eval_accuracy": 0.8027522935779816,
+      "eval_loss": 0.6297979950904846,
+      "eval_runtime": 0.2757,
+      "eval_samples_per_second": 3162.953,
+      "eval_steps_per_second": 14.509,
       "step": 1320
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.08549844473600388,
-      "learning_rate": 0.00088,
-      "loss": 0.6865,
+      "grad_norm": 4.169188976287842,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0955,
       "step": 1584
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.6989858150482178,
-      "eval_runtime": 0.285,
-      "eval_samples_per_second": 3059.492,
-      "eval_steps_per_second": 14.034,
+      "eval_accuracy": 0.7935779816513762,
+      "eval_loss": 0.6731319427490234,
+      "eval_runtime": 0.2813,
+      "eval_samples_per_second": 3100.384,
+      "eval_steps_per_second": 14.222,
       "step": 1584
     },
     {
-      "epoch": 7.0,
-      "grad_norm": 0.5443962216377258,
-      "learning_rate": 0.00086,
-      "loss": 0.6866,
-      "step": 1848
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.5091743119266054,
-      "eval_loss": 0.7005447149276733,
-      "eval_runtime": 0.2848,
-      "eval_samples_per_second": 3061.81,
-      "eval_steps_per_second": 14.045,
-      "step": 1848
-    },
-    {
-      "epoch": 7.0,
-      "step": 1848,
-      "total_flos": 1.2362922335855616e+16,
-      "train_loss": 0.6844654330959568,
-      "train_runtime": 261.6721,
-      "train_samples_per_second": 12868.97,
-      "train_steps_per_second": 50.445
+      "epoch": 6.0,
+      "step": 1584,
+      "total_flos": 1.0596790573590528e+16,
+      "train_loss": 0.19634188305247913,
+      "train_runtime": 225.2591,
+      "train_samples_per_second": 14949.233,
+      "train_steps_per_second": 58.599
     }
   ],
   "logging_steps": 1,
@@ -156,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2362922335855616e+16,
+  "total_flos": 1.0596790573590528e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null