End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: gokulsrinivasagan/bert_base_train_book_ent_15p_s_init
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_train_book_ent_15p_s_init_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
@@ -16,9 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert_base_train_book_ent_15p_s_init_stsb
 
-This model is a fine-tuned version of [gokulsrinivasagan/bert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/bert_base_train_book_ent_15p_s_init) on an unknown dataset.
+This model is a fine-tuned version of [gokulsrinivasagan/bert_base_train_book_ent_15p_s_init](https://huggingface.co/gokulsrinivasagan/bert_base_train_book_ent_15p_s_init) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5971
+- Loss: 2.3759
 - Pearson: nan
 - Spearmanr: nan
 - Combined Score: nan

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": NaN,
+    "eval_loss": 2.3758695125579834,
+    "eval_pearson": NaN,
+    "eval_runtime": 1.3254,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1131.691,
+    "eval_spearmanr": NaN,
+    "eval_steps_per_second": 4.527,
+    "total_flos": 7563059380055040.0,
+    "train_loss": 2.2817909074866254,
+    "train_runtime": 138.8323,
+    "train_samples": 5749,
+    "train_samples_per_second": 2070.483,
+    "train_steps_per_second": 8.283
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_combined_score": NaN,
+    "eval_loss": 2.3758695125579834,
+    "eval_pearson": NaN,
+    "eval_runtime": 1.3254,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1131.691,
+    "eval_spearmanr": NaN,
+    "eval_steps_per_second": 4.527
+}

logs/events.out.tfevents.1745519462.ki-g0008.3436350.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae6e3c31c8f2ea2cfff11c9a9adcabdd63dcc67b6cf6792a96ef0c85577b68a
+size 521

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 7563059380055040.0,
+    "train_loss": 2.2817909074866254,
+    "train_runtime": 138.8323,
+    "train_samples": 5749,
+    "train_samples_per_second": 2070.483,
+    "train_steps_per_second": 8.283
+}

trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_global_step": 115,
+  "best_metric": 2.3758695125579834,
+  "best_model_checkpoint": "bert_base_train_book_ent_15p_s_init_stsb/checkpoint-115",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.842672824859619,
+      "learning_rate": 4.904347826086957e-05,
+      "loss": 3.2768,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.387202262878418,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.269,
+      "eval_samples_per_second": 1182.024,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.728,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.8969907760620117,
+      "learning_rate": 4.804347826086957e-05,
+      "loss": 2.2537,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.5971333980560303,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.2806,
+      "eval_samples_per_second": 1171.301,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.685,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.084527969360352,
+      "learning_rate": 4.7043478260869564e-05,
+      "loss": 2.1653,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.424130916595459,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.2962,
+      "eval_samples_per_second": 1157.201,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.629,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.4313645362854,
+      "learning_rate": 4.6043478260869567e-05,
+      "loss": 2.1567,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.424130916595459,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.323,
+      "eval_samples_per_second": 1133.746,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.535,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.7636301517486572,
+      "learning_rate": 4.504347826086956e-05,
+      "loss": 2.1568,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.3758695125579834,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.2774,
+      "eval_samples_per_second": 1174.222,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.697,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.881765365600586,
+      "learning_rate": 4.404347826086957e-05,
+      "loss": 2.1631,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.3758695125579834,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.2722,
+      "eval_samples_per_second": 1179.099,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.716,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.1646528244018555,
+      "learning_rate": 4.304347826086957e-05,
+      "loss": 2.1703,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.4954440593719482,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.2987,
+      "eval_samples_per_second": 1155.009,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.62,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.207233190536499,
+      "learning_rate": 4.204347826086957e-05,
+      "loss": 2.1686,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.4954440593719482,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.2856,
+      "eval_samples_per_second": 1166.764,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.667,
+      "step": 184
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 14.45374870300293,
+      "learning_rate": 4.104347826086957e-05,
+      "loss": 2.1553,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.4511916637420654,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.2845,
+      "eval_samples_per_second": 1167.788,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.671,
+      "step": 207
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.1430842876434326,
+      "learning_rate": 4.004347826086956e-05,
+      "loss": 2.1512,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "eval_combined_score": NaN,
+      "eval_loss": 2.5971333980560303,
+      "eval_pearson": NaN,
+      "eval_runtime": 1.3192,
+      "eval_samples_per_second": 1137.018,
+      "eval_spearmanr": NaN,
+      "eval_steps_per_second": 4.548,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "step": 230,
+      "total_flos": 7563059380055040.0,
+      "train_loss": 2.2817909074866254,
+      "train_runtime": 138.8323,
+      "train_samples_per_second": 2070.483,
+      "train_steps_per_second": 8.283
+    }
+  ],
+  "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": 7563059380055040.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}