End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_tiny_lda_100_v1_book
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_tiny_lda_100_v1_book_stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.801612109444843
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,12 +30,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_tiny_lda_100_v1_book_stsb
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1_book](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1_book) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8117
-- Pearson: 0.8090
-- Spearmanr: 0.8066
-- Combined Score: 0.8078
+- Loss: 0.7928
+- Pearson: 0.8049
+- Spearmanr: 0.8016
+- Combined Score: 0.8033
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 12.0,
+    "eval_combined_score": 0.8032752057572345,
+    "eval_loss": 0.7928404808044434,
+    "eval_pearson": 0.804938302069626,
+    "eval_runtime": 0.5017,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2989.863,
+    "eval_spearmanr": 0.801612109444843,
+    "eval_steps_per_second": 11.959,
+    "total_flos": 1809057846454272.0,
+    "train_loss": 0.8812504782192949,
+    "train_runtime": 55.1128,
+    "train_samples": 5749,
+    "train_samples_per_second": 5215.669,
+    "train_steps_per_second": 20.866
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 12.0,
+    "eval_combined_score": 0.8032752057572345,
+    "eval_loss": 0.7928404808044434,
+    "eval_pearson": 0.804938302069626,
+    "eval_runtime": 0.5017,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2989.863,
+    "eval_spearmanr": 0.801612109444843,
+    "eval_steps_per_second": 11.959
+}

logs/events.out.tfevents.1733843331.ki-g0008.684565.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c436d12debcbb85953ba9464cf1c240788fbafcf5ef95288650086ad60050af
+size 521

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 12.0,
+    "total_flos": 1809057846454272.0,
+    "train_loss": 0.8812504782192949,
+    "train_runtime": 55.1128,
+    "train_samples": 5749,
+    "train_samples_per_second": 5215.669,
+    "train_steps_per_second": 20.866
+}

trainer_state.json

@@ -0,0 +1,267 @@
+{
+  "best_metric": 0.7928404808044434,
+  "best_model_checkpoint": "bert_tiny_lda_100_v1_book_stsb/checkpoint-161",
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 276,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.924560546875,
+      "learning_rate": 4.9e-05,
+      "loss": 3.1938,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.1298149277779083,
+      "eval_loss": 2.40875506401062,
+      "eval_pearson": 0.12334464647257821,
+      "eval_runtime": 0.4653,
+      "eval_samples_per_second": 3223.457,
+      "eval_spearmanr": 0.13628520908323835,
+      "eval_steps_per_second": 12.894,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.64220142364502,
+      "learning_rate": 4.8e-05,
+      "loss": 1.724,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.6698264576932329,
+      "eval_loss": 1.3508965969085693,
+      "eval_pearson": 0.6694930234855913,
+      "eval_runtime": 0.4916,
+      "eval_samples_per_second": 3051.058,
+      "eval_spearmanr": 0.6701598919008744,
+      "eval_steps_per_second": 12.204,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 12.900686264038086,
+      "learning_rate": 4.7e-05,
+      "loss": 1.1162,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.7639475597706052,
+      "eval_loss": 0.938326358795166,
+      "eval_pearson": 0.7653697327653842,
+      "eval_runtime": 0.5047,
+      "eval_samples_per_second": 2971.952,
+      "eval_spearmanr": 0.7625253867758263,
+      "eval_steps_per_second": 11.888,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 12.227736473083496,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.8449,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.7862762087620649,
+      "eval_loss": 0.8557770848274231,
+      "eval_pearson": 0.7876433771054903,
+      "eval_runtime": 0.4674,
+      "eval_samples_per_second": 3209.347,
+      "eval_spearmanr": 0.7849090404186396,
+      "eval_steps_per_second": 12.837,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 14.088736534118652,
+      "learning_rate": 4.5e-05,
+      "loss": 0.7011,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.7798191089299387,
+      "eval_loss": 0.982633650302887,
+      "eval_pearson": 0.7761116204654516,
+      "eval_runtime": 0.4635,
+      "eval_samples_per_second": 3236.366,
+      "eval_spearmanr": 0.7835265973944259,
+      "eval_steps_per_second": 12.945,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 26.131576538085938,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6154,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.7871494836448947,
+      "eval_loss": 0.8605009913444519,
+      "eval_pearson": 0.7883814228123724,
+      "eval_runtime": 0.4551,
+      "eval_samples_per_second": 3296.061,
+      "eval_spearmanr": 0.7859175444774168,
+      "eval_steps_per_second": 13.184,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 7.498001575469971,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5011,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.8032752057572345,
+      "eval_loss": 0.7928404808044434,
+      "eval_pearson": 0.804938302069626,
+      "eval_runtime": 0.4755,
+      "eval_samples_per_second": 3154.388,
+      "eval_spearmanr": 0.801612109444843,
+      "eval_steps_per_second": 12.618,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 10.33462905883789,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4464,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.8003461198275033,
+      "eval_loss": 0.8498077988624573,
+      "eval_pearson": 0.80085798220367,
+      "eval_runtime": 0.4937,
+      "eval_samples_per_second": 3038.25,
+      "eval_spearmanr": 0.7998342574513366,
+      "eval_steps_per_second": 12.153,
+      "step": 184
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 7.2278923988342285,
+      "learning_rate": 4.1e-05,
+      "loss": 0.3985,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.7983670937253255,
+      "eval_loss": 0.8156148195266724,
+      "eval_pearson": 0.7999059674082583,
+      "eval_runtime": 0.4764,
+      "eval_samples_per_second": 3148.826,
+      "eval_spearmanr": 0.796828220042393,
+      "eval_steps_per_second": 12.595,
+      "step": 207
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 6.5233917236328125,
+      "learning_rate": 4e-05,
+      "loss": 0.3519,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": 0.8038856934960634,
+      "eval_loss": 0.8548710942268372,
+      "eval_pearson": 0.8050016244301849,
+      "eval_runtime": 0.5037,
+      "eval_samples_per_second": 2977.797,
+      "eval_spearmanr": 0.8027697625619419,
+      "eval_steps_per_second": 11.911,
+      "step": 230
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 4.938950061798096,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.366,
+      "step": 253
+    },
+    {
+      "epoch": 11.0,
+      "eval_combined_score": 0.8050210731826717,
+      "eval_loss": 0.8142609000205994,
+      "eval_pearson": 0.8063197444351781,
+      "eval_runtime": 0.478,
+      "eval_samples_per_second": 3138.032,
+      "eval_spearmanr": 0.8037224019301652,
+      "eval_steps_per_second": 12.552,
+      "step": 253
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 9.32435131072998,
+      "learning_rate": 3.8e-05,
+      "loss": 0.3156,
+      "step": 276
+    },
+    {
+      "epoch": 12.0,
+      "eval_combined_score": 0.8077959176146015,
+      "eval_loss": 0.8117431402206421,
+      "eval_pearson": 0.8089959259704242,
+      "eval_runtime": 0.5429,
+      "eval_samples_per_second": 2763.095,
+      "eval_spearmanr": 0.8065959092587788,
+      "eval_steps_per_second": 11.052,
+      "step": 276
+    },
+    {
+      "epoch": 12.0,
+      "step": 276,
+      "total_flos": 1809057846454272.0,
+      "train_loss": 0.8812504782192949,
+      "train_runtime": 55.1128,
+      "train_samples_per_second": 5215.669,
+      "train_steps_per_second": 20.866
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1809057846454272.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}