End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_km_50_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: 0.2801121104631292
 ---
 
 <!-- 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_50_v1_stsb
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_50_v1](https://huggingface.co/Hartunka/bert_base_km_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_50_v1](https://huggingface.co/Hartunka/bert_base_km_50_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5762
-- Pearson: 0.3056
-- Spearmanr: 0.3060
-- Combined Score: 0.3058
+- Loss: 2.1389
+- Pearson: 0.2763
+- Spearmanr: 0.2801
+- Combined Score: 0.2782
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.27823015131617784,
+    "eval_loss": 2.13891863822937,
+    "eval_pearson": 0.27634819216922646,
+    "eval_runtime": 0.9595,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1563.339,
+    "eval_spearmanr": 0.2801121104631292,
+    "eval_steps_per_second": 6.253,
+    "total_flos": 6050447504044032.0,
+    "train_loss": 1.4308352263077446,
+    "train_runtime": 100.0942,
+    "train_samples": 5749,
+    "train_samples_per_second": 2871.795,
+    "train_steps_per_second": 11.489
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.27823015131617784,
+    "eval_loss": 2.13891863822937,
+    "eval_pearson": 0.27634819216922646,
+    "eval_runtime": 0.9595,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1563.339,
+    "eval_spearmanr": 0.2801121104631292,
+    "eval_steps_per_second": 6.253
+}

logs/events.out.tfevents.1745103127.s_005_m.2796520.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40444dfa5c53fc0b57304373e9708a5b115cea55a4ed40b75b11da7728d87eed
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 6050447504044032.0,
+    "train_loss": 1.4308352263077446,
+    "train_runtime": 100.0942,
+    "train_samples": 5749,
+    "train_samples_per_second": 2871.795,
+    "train_steps_per_second": 11.489
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 69,
+  "best_metric": 2.13891863822937,
+  "best_model_checkpoint": "bert_base_km_50_v1_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": 14.298930168151855,
+      "learning_rate": 4.9e-05,
+      "loss": 2.8402,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.20431268932772875,
+      "eval_loss": 2.4772613048553467,
+      "eval_pearson": 0.20675580808289823,
+      "eval_runtime": 0.9909,
+      "eval_samples_per_second": 1513.804,
+      "eval_spearmanr": 0.20186957057255928,
+      "eval_steps_per_second": 6.055,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.726978302001953,
+      "learning_rate": 4.8e-05,
+      "loss": 2.0586,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.22702596907498984,
+      "eval_loss": 2.243328332901001,
+      "eval_pearson": 0.22765342410827677,
+      "eval_runtime": 1.0514,
+      "eval_samples_per_second": 1426.67,
+      "eval_spearmanr": 0.22639851404170291,
+      "eval_steps_per_second": 5.707,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.552237033843994,
+      "learning_rate": 4.7e-05,
+      "loss": 1.8469,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.27823015131617784,
+      "eval_loss": 2.13891863822937,
+      "eval_pearson": 0.27634819216922646,
+      "eval_runtime": 0.948,
+      "eval_samples_per_second": 1582.301,
+      "eval_spearmanr": 0.2801121104631292,
+      "eval_steps_per_second": 6.329,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.038108825683594,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.5476,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.2833951571023935,
+      "eval_loss": 2.307851791381836,
+      "eval_pearson": 0.28322316631141503,
+      "eval_runtime": 0.9719,
+      "eval_samples_per_second": 1543.433,
+      "eval_spearmanr": 0.28356714789337195,
+      "eval_steps_per_second": 6.174,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 9.0367431640625,
+      "learning_rate": 4.5e-05,
+      "loss": 1.1654,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.3019315552492974,
+      "eval_loss": 2.3807790279388428,
+      "eval_pearson": 0.3015344856746127,
+      "eval_runtime": 0.975,
+      "eval_samples_per_second": 1538.43,
+      "eval_spearmanr": 0.3023286248239821,
+      "eval_steps_per_second": 6.154,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 16.923473358154297,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.8754,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.2759957313458622,
+      "eval_loss": 2.527632713317871,
+      "eval_pearson": 0.27689735430889173,
+      "eval_runtime": 0.9711,
+      "eval_samples_per_second": 1544.597,
+      "eval_spearmanr": 0.2750941083828327,
+      "eval_steps_per_second": 6.178,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 8.27717113494873,
+      "learning_rate": 4.3e-05,
+      "loss": 0.6215,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.2901122414894359,
+      "eval_loss": 2.4822278022766113,
+      "eval_pearson": 0.2906590318548305,
+      "eval_runtime": 1.0221,
+      "eval_samples_per_second": 1467.605,
+      "eval_spearmanr": 0.28956545112404125,
+      "eval_steps_per_second": 5.87,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 14.043330192565918,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4911,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.3058001658608961,
+      "eval_loss": 2.5761725902557373,
+      "eval_pearson": 0.3055809401586476,
+      "eval_runtime": 0.9868,
+      "eval_samples_per_second": 1520.067,
+      "eval_spearmanr": 0.3060193915631446,
+      "eval_steps_per_second": 6.08,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "step": 184,
+      "total_flos": 6050447504044032.0,
+      "train_loss": 1.4308352263077446,
+      "train_runtime": 100.0942,
+      "train_samples_per_second": 2871.795,
+      "train_steps_per_second": 11.489
+    }
+  ],
+  "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
+}