End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: gokulsrinivasagan/bert_base_lda_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_lda_100_v1_stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: .nan
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_lda_100_v1_stsb
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_100_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4802
+- Loss: 2.3028
 - Pearson: nan
 - Spearmanr: nan
 - Combined Score: nan

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 15.0,
+    "eval_combined_score": NaN,
+    "eval_loss": 2.302783966064453,
+    "eval_pearson": NaN,
+    "eval_runtime": 0.9609,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1561.041,
+    "eval_spearmanr": NaN,
+    "eval_steps_per_second": 6.244,
+    "total_flos": 1.134458907008256e+16,
+    "train_loss": 2.4118328260338826,
+    "train_runtime": 190.6822,
+    "train_samples": 5749,
+    "train_samples_per_second": 1507.482,
+    "train_steps_per_second": 6.031
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 15.0,
+    "eval_combined_score": NaN,
+    "eval_loss": 2.302783966064453,
+    "eval_pearson": NaN,
+    "eval_runtime": 0.9609,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1561.041,
+    "eval_spearmanr": NaN,
+    "eval_steps_per_second": 6.244
+}

logs/events.out.tfevents.1732650790.ki-g0008.2137866.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec33a4e81fe98d69f668b98ec80972d3bd496eca6254909f5e36a3db977c6669
+size 521

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "total_flos": 1.134458907008256e+16,
+    "train_loss": 2.4118328260338826,
+    "train_runtime": 190.6822,
+    "train_samples": 5749,
+    "train_samples_per_second": 1507.482,
+    "train_steps_per_second": 6.031
+}

trainer_state.json

@@ -0,0 +1,321 @@
+{
+  "best_metric": 2.302783966064453,
+  "best_model_checkpoint": "bert_base_lda_100_v1_stsb/checkpoint-230",
+  "epoch": 15.0,
+  "eval_steps": 500,
+  "global_step": 345,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.897597312927246,
+      "learning_rate": 0.00098,
+      "loss": 5.4876,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.5971333980560303,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.953,
+      "eval_samples_per_second": 1574.03,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.296,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 16.058734893798828,
+      "learning_rate": 0.00096,
+      "loss": 2.2047,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.3758695125579834,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.0004,
+      "eval_samples_per_second": 1499.351,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 5.997,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 11.513495445251465,
+      "learning_rate": 0.00094,
+      "loss": 2.2017,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.4511916637420654,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9743,
+      "eval_samples_per_second": 1539.528,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.158,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.998810768127441,
+      "learning_rate": 0.00092,
+      "loss": 2.1807,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.4511916637420654,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9891,
+      "eval_samples_per_second": 1516.545,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.066,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 17.433738708496094,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 2.1807,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.511171817779541,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9632,
+      "eval_samples_per_second": 1557.271,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.229,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.638427734375,
+      "learning_rate": 0.00088,
+      "loss": 2.196,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.3448002338409424,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9594,
+      "eval_samples_per_second": 1563.421,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.254,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 16.561189651489258,
+      "learning_rate": 0.00086,
+      "loss": 2.1902,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.716400623321533,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9593,
+      "eval_samples_per_second": 1563.575,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.254,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.18385124206543,
+      "learning_rate": 0.00084,
+      "loss": 2.1899,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.6349358558654785,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9637,
+      "eval_samples_per_second": 1556.487,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.226,
+      "step": 184
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 17.808826446533203,
+      "learning_rate": 0.00082,
+      "loss": 2.1962,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.3354201316833496,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9676,
+      "eval_samples_per_second": 1550.299,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.201,
+      "step": 207
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 16.991071701049805,
+      "learning_rate": 0.0008,
+      "loss": 2.1802,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.302783966064453,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9863,
+      "eval_samples_per_second": 1520.902,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.084,
+      "step": 230
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 17.86025619506836,
+      "learning_rate": 0.0007800000000000001,
+      "loss": 2.1945,
+      "step": 253
+    },
+    {
+      "epoch": 11.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.716400623321533,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9587,
+      "eval_samples_per_second": 1564.538,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.258,
+      "step": 253
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 19.099140167236328,
+      "learning_rate": 0.00076,
+      "loss": 2.1932,
+      "step": 276
+    },
+    {
+      "epoch": 12.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.737987518310547,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9594,
+      "eval_samples_per_second": 1563.435,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.254,
+      "step": 276
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 13.359597206115723,
+      "learning_rate": 0.00074,
+      "loss": 2.206,
+      "step": 299
+    },
+    {
+      "epoch": 13.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.737987518310547,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9641,
+      "eval_samples_per_second": 1555.805,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.223,
+      "step": 299
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 5.281756401062012,
+      "learning_rate": 0.0007199999999999999,
+      "loss": 2.1965,
+      "step": 322
+    },
+    {
+      "epoch": 14.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.654569625854492,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9615,
+      "eval_samples_per_second": 1560.105,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.24,
+      "step": 322
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 4.948043346405029,
+      "learning_rate": 0.0007,
+      "loss": 2.1794,
+      "step": 345
+    },
+    {
+      "epoch": 15.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.4802048206329346,
+      "eval_pearson": NaN,
+      "eval_runtime": 0.9617,
+      "eval_samples_per_second": 1559.791,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 6.239,
+      "step": 345
+    },
+    {
+      "epoch": 15.0,
+      "step": 345,
+      "total_flos": 1.134458907008256e+16,
+      "train_loss": 2.4118328260338826,
+      "train_runtime": 190.6822,
+      "train_samples_per_second": 1507.482,
+      "train_steps_per_second": 6.031
+    }
+  ],
+  "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": 1.134458907008256e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}