End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_km_20_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: 0.22422958358388922
 ---
 
 <!-- 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_20_v2_stsb
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6830
-- Pearson: 0.2970
-- Spearmanr: 0.2900
-- Combined Score: 0.2935
+- Loss: 2.2841
+- Pearson: 0.2453
+- Spearmanr: 0.2242
+- Combined Score: 0.2348
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.2347506487760969,
+    "eval_loss": 2.284109115600586,
+    "eval_pearson": 0.24527171396830455,
+    "eval_runtime": 0.9874,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1519.172,
+    "eval_spearmanr": 0.22422958358388922,
+    "eval_steps_per_second": 6.077,
+    "total_flos": 6050447504044032.0,
+    "train_loss": 1.361802137416342,
+    "train_runtime": 101.9405,
+    "train_samples": 5749,
+    "train_samples_per_second": 2819.781,
+    "train_steps_per_second": 11.281
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.2347506487760969,
+    "eval_loss": 2.284109115600586,
+    "eval_pearson": 0.24527171396830455,
+    "eval_runtime": 0.9874,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1519.172,
+    "eval_spearmanr": 0.22422958358388922,
+    "eval_steps_per_second": 6.077
+}

logs/events.out.tfevents.1745405086.s_005_m.2876923.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5026437a4905e393bf66c6706df27420e060dc50984ddc63d61606b3feb92e50
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 6050447504044032.0,
+    "train_loss": 1.361802137416342,
+    "train_runtime": 101.9405,
+    "train_samples": 5749,
+    "train_samples_per_second": 2819.781,
+    "train_steps_per_second": 11.281
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 69,
+  "best_metric": 2.284109115600586,
+  "best_model_checkpoint": "bert_base_km_20_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": 7.806451320648193,
+      "learning_rate": 4.9e-05,
+      "loss": 2.8315,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.17325126314917527,
+      "eval_loss": 2.3672611713409424,
+      "eval_pearson": 0.17680364716836725,
+      "eval_runtime": 0.9671,
+      "eval_samples_per_second": 1551.082,
+      "eval_spearmanr": 0.16969887912998333,
+      "eval_steps_per_second": 6.204,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.039875030517578,
+      "learning_rate": 4.8e-05,
+      "loss": 1.9303,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.20889048526655812,
+      "eval_loss": 2.288813829421997,
+      "eval_pearson": 0.2169855182534226,
+      "eval_runtime": 1.0141,
+      "eval_samples_per_second": 1479.09,
+      "eval_spearmanr": 0.20079545227969361,
+      "eval_steps_per_second": 5.916,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.271673679351807,
+      "learning_rate": 4.7e-05,
+      "loss": 1.709,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.2347506487760969,
+      "eval_loss": 2.284109115600586,
+      "eval_pearson": 0.24527171396830455,
+      "eval_runtime": 0.9763,
+      "eval_samples_per_second": 1536.411,
+      "eval_spearmanr": 0.22422958358388922,
+      "eval_steps_per_second": 6.146,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.751137733459473,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.4178,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.23890222674042505,
+      "eval_loss": 2.4758355617523193,
+      "eval_pearson": 0.2474864689083224,
+      "eval_runtime": 0.9837,
+      "eval_samples_per_second": 1524.782,
+      "eval_spearmanr": 0.23031798457252767,
+      "eval_steps_per_second": 6.099,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 11.457999229431152,
+      "learning_rate": 4.5e-05,
+      "loss": 1.0869,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.2556854902547276,
+      "eval_loss": 2.640655279159546,
+      "eval_pearson": 0.2645669748777482,
+      "eval_runtime": 0.9933,
+      "eval_samples_per_second": 1510.175,
+      "eval_spearmanr": 0.24680400563170699,
+      "eval_steps_per_second": 6.041,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 10.299137115478516,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.8003,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.30113251572530986,
+      "eval_loss": 2.4700069427490234,
+      "eval_pearson": 0.30421638459279976,
+      "eval_runtime": 0.9544,
+      "eval_samples_per_second": 1571.595,
+      "eval_spearmanr": 0.29804864685781995,
+      "eval_steps_per_second": 6.286,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 7.1300458908081055,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6337,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.32282905472719853,
+      "eval_loss": 2.4532406330108643,
+      "eval_pearson": 0.32045874948102093,
+      "eval_runtime": 1.0099,
+      "eval_samples_per_second": 1485.339,
+      "eval_spearmanr": 0.3251993599733761,
+      "eval_steps_per_second": 5.941,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 8.175042152404785,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4849,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.2934684357397273,
+      "eval_loss": 2.683006525039673,
+      "eval_pearson": 0.2969667423436427,
+      "eval_runtime": 0.9649,
+      "eval_samples_per_second": 1554.598,
+      "eval_spearmanr": 0.28997012913581194,
+      "eval_steps_per_second": 6.218,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "step": 184,
+      "total_flos": 6050447504044032.0,
+      "train_loss": 1.361802137416342,
+      "train_runtime": 101.9405,
+      "train_samples_per_second": 2819.781,
+      "train_steps_per_second": 11.281
+    }
+  ],
+  "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
+}