End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_rand_5_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: 0.19834161286191287
 ---
 
 <!-- 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_base_rand_5_v1_stsb
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v1](https://huggingface.co/Hartunka/bert_base_rand_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v1](https://huggingface.co/Hartunka/bert_base_rand_5_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3986
-- Pearson: 0.3379
-- Spearmanr: 0.3299
-- Combined Score: 0.3339
+- Loss: 2.2682
+- Pearson: 0.2151
+- Spearmanr: 0.1983
+- Combined Score: 0.2067
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_combined_score": 0.20672083674789737,
+    "eval_loss": 2.2682323455810547,
+    "eval_pearson": 0.2151000606338819,
+    "eval_runtime": 0.9698,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1546.755,
+    "eval_spearmanr": 0.19834161286191287,
+    "eval_steps_per_second": 6.187,
+    "total_flos": 5294141566038528.0,
+    "train_loss": 1.3701281044053735,
+    "train_runtime": 86.1047,
+    "train_samples": 5749,
+    "train_samples_per_second": 3338.376,
+    "train_steps_per_second": 13.356
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_combined_score": 0.20672083674789737,
+    "eval_loss": 2.2682323455810547,
+    "eval_pearson": 0.2151000606338819,
+    "eval_runtime": 0.9698,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1546.755,
+    "eval_spearmanr": 0.19834161286191287,
+    "eval_steps_per_second": 6.187
+}

logs/events.out.tfevents.1745127303.s_005_m.2796520.49

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff90b29db25e9c95376b279f8c879480908c954d796354498fac160295187e3
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 5294141566038528.0,
+    "train_loss": 1.3701281044053735,
+    "train_runtime": 86.1047,
+    "train_samples": 5749,
+    "train_samples_per_second": 3338.376,
+    "train_steps_per_second": 13.356
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 46,
+  "best_metric": 2.2682323455810547,
+  "best_model_checkpoint": "bert_base_rand_5_v1_stsb/checkpoint-46",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 161,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.10588264465332,
+      "learning_rate": 4.9e-05,
+      "loss": 2.7364,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.08826959707132218,
+      "eval_loss": 2.7826881408691406,
+      "eval_pearson": 0.09631910596498261,
+      "eval_runtime": 0.9537,
+      "eval_samples_per_second": 1572.774,
+      "eval_spearmanr": 0.08022008817766174,
+      "eval_steps_per_second": 6.291,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 14.48088550567627,
+      "learning_rate": 4.8e-05,
+      "loss": 1.8997,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.20672083674789737,
+      "eval_loss": 2.2682323455810547,
+      "eval_pearson": 0.2151000606338819,
+      "eval_runtime": 0.9667,
+      "eval_samples_per_second": 1551.735,
+      "eval_spearmanr": 0.19834161286191287,
+      "eval_steps_per_second": 6.207,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.782012939453125,
+      "learning_rate": 4.7e-05,
+      "loss": 1.5738,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.27437339110149783,
+      "eval_loss": 2.354666233062744,
+      "eval_pearson": 0.2810730442397911,
+      "eval_runtime": 0.9802,
+      "eval_samples_per_second": 1530.376,
+      "eval_spearmanr": 0.26767373796320454,
+      "eval_steps_per_second": 6.122,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 13.505708694458008,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.242,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.3116044048067962,
+      "eval_loss": 2.378068208694458,
+      "eval_pearson": 0.31203276845328737,
+      "eval_runtime": 0.9419,
+      "eval_samples_per_second": 1592.541,
+      "eval_spearmanr": 0.31117604116030495,
+      "eval_steps_per_second": 6.37,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 22.02513313293457,
+      "learning_rate": 4.5e-05,
+      "loss": 0.8939,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.3197932867485796,
+      "eval_loss": 2.472320318222046,
+      "eval_pearson": 0.3232025649696559,
+      "eval_runtime": 0.9748,
+      "eval_samples_per_second": 1538.755,
+      "eval_spearmanr": 0.3163840085275033,
+      "eval_steps_per_second": 6.155,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 10.271648406982422,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.725,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.31174214225237584,
+      "eval_loss": 2.5859534740448,
+      "eval_pearson": 0.318089983487546,
+      "eval_runtime": 0.9885,
+      "eval_samples_per_second": 1517.437,
+      "eval_spearmanr": 0.3053943010172056,
+      "eval_steps_per_second": 6.07,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 8.576903343200684,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5201,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.333876543504556,
+      "eval_loss": 2.3985676765441895,
+      "eval_pearson": 0.3378705623208662,
+      "eval_runtime": 0.9524,
+      "eval_samples_per_second": 1575.031,
+      "eval_spearmanr": 0.32988252468824575,
+      "eval_steps_per_second": 6.3,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "step": 161,
+      "total_flos": 5294141566038528.0,
+      "train_loss": 1.3701281044053735,
+      "train_runtime": 86.1047,
+      "train_samples_per_second": 3338.376,
+      "train_steps_per_second": 13.356
+    }
+  ],
+  "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": 5294141566038528.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}