End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_100_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_km_100_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: 0.22813141234967038
 ---
 
 <!-- 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_km_100_v2_stsb
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_100_v2](https://huggingface.co/Hartunka/bert_base_km_100_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_100_v2](https://huggingface.co/Hartunka/bert_base_km_100_v2) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6081
-- Pearson: 0.3154
-- Spearmanr: 0.3114
-- Combined Score: 0.3134
+- Loss: 2.2511
+- Pearson: 0.2543
+- Spearmanr: 0.2281
+- Combined Score: 0.2412
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.24123421383218868,
+    "eval_loss": 2.2510719299316406,
+    "eval_pearson": 0.254337015314707,
+    "eval_runtime": 1.0008,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1498.811,
+    "eval_spearmanr": 0.22813141234967038,
+    "eval_steps_per_second": 5.995,
+    "total_flos": 6050447504044032.0,
+    "train_loss": 1.3881200811137324,
+    "train_runtime": 100.0781,
+    "train_samples": 5749,
+    "train_samples_per_second": 2872.256,
+    "train_steps_per_second": 11.491
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.24123421383218868,
+    "eval_loss": 2.2510719299316406,
+    "eval_pearson": 0.254337015314707,
+    "eval_runtime": 1.0008,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1498.811,
+    "eval_spearmanr": 0.22813141234967038,
+    "eval_steps_per_second": 5.995
+}

logs/events.out.tfevents.1745449892.s_005_m.2892304.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364dafeedf29765c5e82ef307f05c1bc004da88bccefde583f6210009748eded
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 6050447504044032.0,
+    "train_loss": 1.3881200811137324,
+    "train_runtime": 100.0781,
+    "train_samples": 5749,
+    "train_samples_per_second": 2872.256,
+    "train_steps_per_second": 11.491
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 69,
+  "best_metric": 2.2510719299316406,
+  "best_model_checkpoint": "bert_base_km_100_v2_stsb/checkpoint-69",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 184,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.3268890380859375,
+      "learning_rate": 4.9e-05,
+      "loss": 2.8847,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.1391444636598853,
+      "eval_loss": 2.3409430980682373,
+      "eval_pearson": 0.14273382335013363,
+      "eval_runtime": 0.9579,
+      "eval_samples_per_second": 1565.907,
+      "eval_spearmanr": 0.13555510396963702,
+      "eval_steps_per_second": 6.264,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.743993759155273,
+      "learning_rate": 4.8e-05,
+      "loss": 1.9403,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.22169014487829902,
+      "eval_loss": 2.2677249908447266,
+      "eval_pearson": 0.23351683650146088,
+      "eval_runtime": 0.9727,
+      "eval_samples_per_second": 1542.178,
+      "eval_spearmanr": 0.2098634532551372,
+      "eval_steps_per_second": 6.169,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.372401714324951,
+      "learning_rate": 4.7e-05,
+      "loss": 1.717,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.24123421383218868,
+      "eval_loss": 2.2510719299316406,
+      "eval_pearson": 0.254337015314707,
+      "eval_runtime": 0.9625,
+      "eval_samples_per_second": 1558.489,
+      "eval_spearmanr": 0.22813141234967038,
+      "eval_steps_per_second": 6.234,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.017662048339844,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.4331,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.2368341721311384,
+      "eval_loss": 2.47322940826416,
+      "eval_pearson": 0.2500560641880369,
+      "eval_runtime": 0.9931,
+      "eval_samples_per_second": 1510.382,
+      "eval_spearmanr": 0.22361228007423992,
+      "eval_steps_per_second": 6.042,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 9.426039695739746,
+      "learning_rate": 4.5e-05,
+      "loss": 1.1074,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.2846047849390027,
+      "eval_loss": 2.5301966667175293,
+      "eval_pearson": 0.2919352546278261,
+      "eval_runtime": 0.9677,
+      "eval_samples_per_second": 1550.061,
+      "eval_spearmanr": 0.2772743152501793,
+      "eval_steps_per_second": 6.2,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 9.062575340270996,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.8742,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.34415755673786286,
+      "eval_loss": 2.2740066051483154,
+      "eval_pearson": 0.34197047561182364,
+      "eval_runtime": 0.9979,
+      "eval_samples_per_second": 1503.156,
+      "eval_spearmanr": 0.346344637863902,
+      "eval_steps_per_second": 6.013,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 8.04768180847168,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6435,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.32730671366098585,
+      "eval_loss": 2.485415458679199,
+      "eval_pearson": 0.32840219738195314,
+      "eval_runtime": 0.9618,
+      "eval_samples_per_second": 1559.519,
+      "eval_spearmanr": 0.3262112299400186,
+      "eval_steps_per_second": 6.238,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 9.937243461608887,
+      "learning_rate": 4.2e-05,
+      "loss": 0.5047,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.31341031479510106,
+      "eval_loss": 2.6080784797668457,
+      "eval_pearson": 0.31538213675289933,
+      "eval_runtime": 0.9884,
+      "eval_samples_per_second": 1517.654,
+      "eval_spearmanr": 0.31143849283730274,
+      "eval_steps_per_second": 6.071,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "step": 184,
+      "total_flos": 6050447504044032.0,
+      "train_loss": 1.3881200811137324,
+      "train_runtime": 100.0781,
+      "train_samples_per_second": 2872.256,
+      "train_steps_per_second": 11.491
+    }
+  ],
+  "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": 6050447504044032.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}