End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_rand_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_rand_5_v2_stsb
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE STSB
+      type: glue
+      args: stsb
+    metrics:
+    - name: Spearmanr
+      type: spearmanr
+      value: 0.16189439146929932
 ---
 
 <!-- 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_v2_stsb
 
-This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v2](https://huggingface.co/Hartunka/bert_base_rand_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v2](https://huggingface.co/Hartunka/bert_base_rand_5_v2) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3745
-- Pearson: 0.3379
-- Spearmanr: 0.3323
-- Combined Score: 0.3351
+- Loss: 2.3163
+- Pearson: 0.1954
+- Spearmanr: 0.1619
+- Combined Score: 0.1787
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_combined_score": 0.17865816941006596,
+    "eval_loss": 2.3162741661071777,
+    "eval_pearson": 0.19542194735083257,
+    "eval_runtime": 0.9774,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1534.63,
+    "eval_spearmanr": 0.16189439146929932,
+    "eval_steps_per_second": 6.139,
+    "total_flos": 5294141566038528.0,
+    "train_loss": 1.3533399475287207,
+    "train_runtime": 88.0763,
+    "train_samples": 5749,
+    "train_samples_per_second": 3263.646,
+    "train_steps_per_second": 13.057
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_combined_score": 0.17865816941006596,
+    "eval_loss": 2.3162741661071777,
+    "eval_pearson": 0.19542194735083257,
+    "eval_runtime": 0.9774,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1534.63,
+    "eval_spearmanr": 0.16189439146929932,
+    "eval_steps_per_second": 6.139
+}

logs/events.out.tfevents.1745462657.s_005_m.2892304.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97fdb3f7a5b771c38491a2491d6f8e07ea0e114d384795f939a4d1b5d87f901f
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 5294141566038528.0,
+    "train_loss": 1.3533399475287207,
+    "train_runtime": 88.0763,
+    "train_samples": 5749,
+    "train_samples_per_second": 3263.646,
+    "train_steps_per_second": 13.057
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 46,
+  "best_metric": 2.3162741661071777,
+  "best_model_checkpoint": "bert_base_rand_5_v2_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": 4.672378063201904,
+      "learning_rate": 4.9e-05,
+      "loss": 2.6563,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.09050440946239476,
+      "eval_loss": 2.468899726867676,
+      "eval_pearson": 0.09885560057722062,
+      "eval_runtime": 0.9893,
+      "eval_samples_per_second": 1516.155,
+      "eval_spearmanr": 0.08215321834756889,
+      "eval_steps_per_second": 6.065,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.538728713989258,
+      "learning_rate": 4.8e-05,
+      "loss": 1.8843,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.17865816941006596,
+      "eval_loss": 2.3162741661071777,
+      "eval_pearson": 0.19542194735083257,
+      "eval_runtime": 1.003,
+      "eval_samples_per_second": 1495.455,
+      "eval_spearmanr": 0.16189439146929932,
+      "eval_steps_per_second": 5.982,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.898491859436035,
+      "learning_rate": 4.7e-05,
+      "loss": 1.6315,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.25567049594755953,
+      "eval_loss": 2.365222930908203,
+      "eval_pearson": 0.26043384251429863,
+      "eval_runtime": 0.9606,
+      "eval_samples_per_second": 1561.529,
+      "eval_spearmanr": 0.25090714938082037,
+      "eval_steps_per_second": 6.246,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 10.290682792663574,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.2245,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.28864361414381867,
+      "eval_loss": 2.5701653957366943,
+      "eval_pearson": 0.2910950881475413,
+      "eval_runtime": 0.9942,
+      "eval_samples_per_second": 1508.822,
+      "eval_spearmanr": 0.286192140140096,
+      "eval_steps_per_second": 6.035,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 11.64109992980957,
+      "learning_rate": 4.5e-05,
+      "loss": 0.8986,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.27109561622168327,
+      "eval_loss": 2.6825172901153564,
+      "eval_pearson": 0.27674054063954884,
+      "eval_runtime": 0.9605,
+      "eval_samples_per_second": 1561.745,
+      "eval_spearmanr": 0.2654506918038177,
+      "eval_steps_per_second": 6.247,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.450591564178467,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.6617,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.30805346136071465,
+      "eval_loss": 2.512233018875122,
+      "eval_pearson": 0.3120714777686556,
+      "eval_runtime": 1.0131,
+      "eval_samples_per_second": 1480.655,
+      "eval_spearmanr": 0.3040354449527736,
+      "eval_steps_per_second": 5.923,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 12.366684913635254,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5165,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.33508237397612906,
+      "eval_loss": 2.374462127685547,
+      "eval_pearson": 0.3379127982925731,
+      "eval_runtime": 0.9637,
+      "eval_samples_per_second": 1556.566,
+      "eval_spearmanr": 0.332251949659685,
+      "eval_steps_per_second": 6.226,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "step": 161,
+      "total_flos": 5294141566038528.0,
+      "train_loss": 1.3533399475287207,
+      "train_runtime": 88.0763,
+      "train_samples_per_second": 3263.646,
+      "train_steps_per_second": 13.057
+    }
+  ],
+  "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
+}