End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert_tiny_lda_20_v1_mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6954841334418226
 ---
 
 <!-- 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_20_v1_mnli
 
-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 MNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8428
-- Accuracy: 0.6963
+- Loss: 0.7126
+- Accuracy: 0.6955
 
 ## Model description
 

all_results.json

@@ -1,22 +1,22 @@
 {
-    "epoch": 7.0,
-    "epoch_mm": 7.0,
-    "eval_accuracy": 0.3544574630667346,
-    "eval_accuracy_mm": 0.3522172497965826,
-    "eval_loss": 1.0962358713150024,
-    "eval_loss_mm": 1.0962363481521606,
-    "eval_runtime": 3.0533,
-    "eval_runtime_mm": 3.0458,
+    "epoch": 9.0,
+    "epoch_mm": 9.0,
+    "eval_accuracy": 0.6861946001018848,
+    "eval_accuracy_mm": 0.6954841334418226,
+    "eval_loss": 0.7247127294540405,
+    "eval_loss_mm": 0.7125838994979858,
+    "eval_runtime": 3.058,
+    "eval_runtime_mm": 3.0193,
     "eval_samples": 9815,
     "eval_samples_mm": 9832,
-    "eval_samples_per_second": 3214.548,
-    "eval_samples_per_second_mm": 3228.061,
-    "eval_steps_per_second": 12.773,
-    "eval_steps_per_second_mm": 12.805,
-    "total_flos": 7.208852705843712e+16,
-    "train_loss": 1.0986731009324362,
-    "train_runtime": 1497.1474,
+    "eval_samples_per_second": 3209.632,
+    "eval_samples_per_second_mm": 3256.415,
+    "eval_steps_per_second": 12.754,
+    "eval_steps_per_second_mm": 12.917,
+    "total_flos": 9.268524907513344e+16,
+    "train_loss": 0.6734655303711928,
+    "train_runtime": 1930.2365,
     "train_samples": 392702,
-    "train_samples_per_second": 13115.008,
-    "train_steps_per_second": 51.231
+    "train_samples_per_second": 10172.38,
+    "train_steps_per_second": 39.736
 }

eval_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 7.0,
-    "epoch_mm": 7.0,
-    "eval_accuracy": 0.3544574630667346,
-    "eval_accuracy_mm": 0.3522172497965826,
-    "eval_loss": 1.0962358713150024,
-    "eval_loss_mm": 1.0962363481521606,
-    "eval_runtime": 3.0533,
-    "eval_runtime_mm": 3.0458,
+    "epoch": 9.0,
+    "epoch_mm": 9.0,
+    "eval_accuracy": 0.6861946001018848,
+    "eval_accuracy_mm": 0.6954841334418226,
+    "eval_loss": 0.7247127294540405,
+    "eval_loss_mm": 0.7125838994979858,
+    "eval_runtime": 3.058,
+    "eval_runtime_mm": 3.0193,
     "eval_samples": 9815,
     "eval_samples_mm": 9832,
-    "eval_samples_per_second": 3214.548,
-    "eval_samples_per_second_mm": 3228.061,
-    "eval_steps_per_second": 12.773,
-    "eval_steps_per_second_mm": 12.805
+    "eval_samples_per_second": 3209.632,
+    "eval_samples_per_second_mm": 3256.415,
+    "eval_steps_per_second": 12.754,
+    "eval_steps_per_second_mm": 12.917
 }

logs/events.out.tfevents.1733328140.ki-g0008.1207389.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b5a9043a84ea3b31733feca475517d965e67f9edcb6b364c61a416bd30ced4
+size 734

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 7.0,
-    "total_flos": 7.208852705843712e+16,
-    "train_loss": 1.0986731009324362,
-    "train_runtime": 1497.1474,
+    "epoch": 9.0,
+    "total_flos": 9.268524907513344e+16,
+    "train_loss": 0.6734655303711928,
+    "train_runtime": 1930.2365,
     "train_samples": 392702,
-    "train_samples_per_second": 13115.008,
-    "train_steps_per_second": 51.231
+    "train_samples_per_second": 10172.38,
+    "train_steps_per_second": 39.736
 }

trainer_state.json

@@ -1,133 +1,165 @@
 {
-  "best_metric": 1.0962358713150024,
-  "best_model_checkpoint": "bert_tiny_lda_20_v1_mnli/checkpoint-3068",
-  "epoch": 7.0,
+  "best_metric": 0.7247127294540405,
+  "best_model_checkpoint": "bert_tiny_lda_20_v1_mnli/checkpoint-6136",
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 10738,
+  "global_step": 13806,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.02029508352279663,
-      "learning_rate": 0.00098,
-      "loss": 1.0993,
+      "grad_norm": 1.368187427520752,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9696,
       "step": 1534
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.3273560876209883,
-      "eval_loss": 1.0992883443832397,
-      "eval_runtime": 2.9964,
-      "eval_samples_per_second": 3275.549,
-      "eval_steps_per_second": 13.015,
+      "eval_accuracy": 0.6101884870096791,
+      "eval_loss": 0.8634526133537292,
+      "eval_runtime": 3.0133,
+      "eval_samples_per_second": 3257.2,
+      "eval_steps_per_second": 12.943,
       "step": 1534
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.11836767196655273,
-      "learning_rate": 0.00096,
-      "loss": 1.0986,
+      "grad_norm": 1.6427279710769653,
+      "learning_rate": 4.8e-05,
+      "loss": 0.8307,
       "step": 3068
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.3544574630667346,
-      "eval_loss": 1.0962358713150024,
-      "eval_runtime": 3.0153,
-      "eval_samples_per_second": 3255.045,
-      "eval_steps_per_second": 12.934,
+      "eval_accuracy": 0.650127356087621,
+      "eval_loss": 0.7848993539810181,
+      "eval_runtime": 2.9642,
+      "eval_samples_per_second": 3311.169,
+      "eval_steps_per_second": 13.157,
       "step": 3068
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.03678739443421364,
-      "learning_rate": 0.00094,
-      "loss": 1.0987,
+      "grad_norm": 1.6854288578033447,
+      "learning_rate": 4.7e-05,
+      "loss": 0.7523,
       "step": 4602
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.3273560876209883,
-      "eval_loss": 1.0964475870132446,
-      "eval_runtime": 3.0346,
-      "eval_samples_per_second": 3234.397,
-      "eval_steps_per_second": 12.852,
+      "eval_accuracy": 0.6728476821192053,
+      "eval_loss": 0.7466796040534973,
+      "eval_runtime": 3.0301,
+      "eval_samples_per_second": 3239.134,
+      "eval_steps_per_second": 12.871,
       "step": 4602
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.062206000089645386,
-      "learning_rate": 0.00092,
-      "loss": 1.0985,
+      "grad_norm": 2.0163750648498535,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.6962,
       "step": 6136
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.31818644931227713,
-      "eval_loss": 1.10163414478302,
-      "eval_runtime": 3.0235,
-      "eval_samples_per_second": 3246.215,
-      "eval_steps_per_second": 12.899,
+      "eval_accuracy": 0.6861946001018848,
+      "eval_loss": 0.7247127294540405,
+      "eval_runtime": 2.956,
+      "eval_samples_per_second": 3320.356,
+      "eval_steps_per_second": 13.193,
       "step": 6136
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.07343439757823944,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 1.0985,
+      "grad_norm": 1.9129326343536377,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6472,
       "step": 7670
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.3544574630667346,
-      "eval_loss": 1.0988649129867554,
-      "eval_runtime": 3.0456,
-      "eval_samples_per_second": 3222.725,
-      "eval_steps_per_second": 12.806,
+      "eval_accuracy": 0.6956698930208864,
+      "eval_loss": 0.7247539162635803,
+      "eval_runtime": 3.0432,
+      "eval_samples_per_second": 3225.221,
+      "eval_steps_per_second": 12.815,
       "step": 7670
     },
     {
       "epoch": 6.0,
-      "grad_norm": 0.047856856137514114,
-      "learning_rate": 0.00088,
-      "loss": 1.0986,
+      "grad_norm": 2.0681214332580566,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6032,
       "step": 9204
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.3544574630667346,
-      "eval_loss": 1.0988649129867554,
-      "eval_runtime": 3.0238,
-      "eval_samples_per_second": 3245.866,
-      "eval_steps_per_second": 12.897,
+      "eval_accuracy": 0.6984207845134998,
+      "eval_loss": 0.7455375790596008,
+      "eval_runtime": 3.0056,
+      "eval_samples_per_second": 3265.623,
+      "eval_steps_per_second": 12.976,
       "step": 9204
     },
     {
       "epoch": 7.0,
-      "grad_norm": 0.0775880515575409,
-      "learning_rate": 0.00086,
-      "loss": 1.0986,
+      "grad_norm": 1.9462851285934448,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5606,
       "step": 10738
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.31818644931227713,
-      "eval_loss": 1.0992883443832397,
-      "eval_runtime": 3.0565,
-      "eval_samples_per_second": 3211.238,
-      "eval_steps_per_second": 12.76,
+      "eval_accuracy": 0.6987264391237901,
+      "eval_loss": 0.7510461807250977,
+      "eval_runtime": 3.0013,
+      "eval_samples_per_second": 3270.26,
+      "eval_steps_per_second": 12.994,
       "step": 10738
     },
     {
-      "epoch": 7.0,
-      "step": 10738,
-      "total_flos": 7.208852705843712e+16,
-      "train_loss": 1.0986731009324362,
-      "train_runtime": 1497.1474,
-      "train_samples_per_second": 13115.008,
-      "train_steps_per_second": 51.231
+      "epoch": 8.0,
+      "grad_norm": 2.2662479877471924,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5204,
+      "step": 12272
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.691492613346918,
+      "eval_loss": 0.7848535776138306,
+      "eval_runtime": 2.9767,
+      "eval_samples_per_second": 3297.3,
+      "eval_steps_per_second": 13.102,
+      "step": 12272
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.846130847930908,
+      "learning_rate": 4.1e-05,
+      "loss": 0.4808,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6962812022414672,
+      "eval_loss": 0.8428312540054321,
+      "eval_runtime": 2.9346,
+      "eval_samples_per_second": 3344.624,
+      "eval_steps_per_second": 13.29,
+      "step": 13806
+    },
+    {
+      "epoch": 9.0,
+      "step": 13806,
+      "total_flos": 9.268524907513344e+16,
+      "train_loss": 0.6734655303711928,
+      "train_runtime": 1930.2365,
+      "train_samples_per_second": 10172.38,
+      "train_steps_per_second": 39.736
     }
   ],
   "logging_steps": 1,
@@ -156,7 +188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.208852705843712e+16,
+  "total_flos": 9.268524907513344e+16,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null