End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_20_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_km_20_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: 0.2806848266082787
 ---
 
 <!-- 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_v1_stsb
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4996
-- Pearson: 0.3085
-- Spearmanr: 0.3151
-- Combined Score: 0.3118
+- Loss: 2.1734
+- Pearson: 0.2765
+- Spearmanr: 0.2807
+- Combined Score: 0.2786
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.27859606936951653,
+    "eval_loss": 2.1733975410461426,
+    "eval_pearson": 0.27650731213075436,
+    "eval_runtime": 0.9705,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1545.65,
+    "eval_spearmanr": 0.2806848266082787,
+    "eval_steps_per_second": 6.183,
+    "total_flos": 6050447504044032.0,
+    "train_loss": 1.3817211441371753,
+    "train_runtime": 98.0352,
+    "train_samples": 5749,
+    "train_samples_per_second": 2932.112,
+    "train_steps_per_second": 11.73
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.27859606936951653,
+    "eval_loss": 2.1733975410461426,
+    "eval_pearson": 0.27650731213075436,
+    "eval_runtime": 0.9705,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1545.65,
+    "eval_spearmanr": 0.2806848266082787,
+    "eval_steps_per_second": 6.183
+}

logs/events.out.tfevents.1745035073.s_005_m.2780655.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6228ae61874b8a05f7a94fadc50aa2d16f00c5cd849803ebf8ff8b1ef6bc78
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 6050447504044032.0,
+    "train_loss": 1.3817211441371753,
+    "train_runtime": 98.0352,
+    "train_samples": 5749,
+    "train_samples_per_second": 2932.112,
+    "train_steps_per_second": 11.73
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 69,
+  "best_metric": 2.1733975410461426,
+  "best_model_checkpoint": "bert_base_km_20_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": 12.473910331726074,
+      "learning_rate": 4.9e-05,
+      "loss": 2.7536,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.21883840300992635,
+      "eval_loss": 2.362926721572876,
+      "eval_pearson": 0.22315559305765864,
+      "eval_runtime": 0.9514,
+      "eval_samples_per_second": 1576.685,
+      "eval_spearmanr": 0.21452121296219404,
+      "eval_steps_per_second": 6.307,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.219836235046387,
+      "learning_rate": 4.8e-05,
+      "loss": 2.0466,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.2250433116133167,
+      "eval_loss": 2.223330020904541,
+      "eval_pearson": 0.22643903431708493,
+      "eval_runtime": 0.9766,
+      "eval_samples_per_second": 1536.013,
+      "eval_spearmanr": 0.2236475889095485,
+      "eval_steps_per_second": 6.144,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.506649017333984,
+      "learning_rate": 4.7e-05,
+      "loss": 1.83,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.27859606936951653,
+      "eval_loss": 2.1733975410461426,
+      "eval_pearson": 0.27650731213075436,
+      "eval_runtime": 0.9499,
+      "eval_samples_per_second": 1579.115,
+      "eval_spearmanr": 0.2806848266082787,
+      "eval_steps_per_second": 6.316,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.99960994720459,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.488,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.2857232862338934,
+      "eval_loss": 2.284653902053833,
+      "eval_pearson": 0.28481215085198996,
+      "eval_runtime": 0.9437,
+      "eval_samples_per_second": 1589.456,
+      "eval_spearmanr": 0.28663442161579694,
+      "eval_steps_per_second": 6.358,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 17.941621780395508,
+      "learning_rate": 4.5e-05,
+      "loss": 1.1184,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.2801317348206342,
+      "eval_loss": 2.755934238433838,
+      "eval_pearson": 0.27054585694075417,
+      "eval_runtime": 0.997,
+      "eval_samples_per_second": 1504.452,
+      "eval_spearmanr": 0.2897176127005142,
+      "eval_steps_per_second": 6.018,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.229860305786133,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.836,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.30899397408639784,
+      "eval_loss": 2.474417209625244,
+      "eval_pearson": 0.3009404135965045,
+      "eval_runtime": 0.9611,
+      "eval_samples_per_second": 1560.688,
+      "eval_spearmanr": 0.31704753457629126,
+      "eval_steps_per_second": 6.243,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.495700836181641,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5651,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.2980624641456129,
+      "eval_loss": 2.5624561309814453,
+      "eval_pearson": 0.29500261904772385,
+      "eval_runtime": 0.994,
+      "eval_samples_per_second": 1508.988,
+      "eval_spearmanr": 0.301122309243502,
+      "eval_steps_per_second": 6.036,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 5.729962348937988,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4161,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.31179634058913464,
+      "eval_loss": 2.499624252319336,
+      "eval_pearson": 0.3084881703414194,
+      "eval_runtime": 0.9583,
+      "eval_samples_per_second": 1565.335,
+      "eval_spearmanr": 0.3151045108368498,
+      "eval_steps_per_second": 6.261,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "step": 184,
+      "total_flos": 6050447504044032.0,
+      "train_loss": 1.3817211441371753,
+      "train_runtime": 98.0352,
+      "train_samples_per_second": 2932.112,
+      "train_steps_per_second": 11.73
+    }
+  ],
+  "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
+}