End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/bert_base_km_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: bert_base_km_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: 0.4647300879795164
 ---
 
 <!-- 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_5_v2_stsb
 
-This model is a fine-tuned version of [Hartunka/bert_base_km_5_v2](https://huggingface.co/Hartunka/bert_base_km_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/bert_base_km_5_v2](https://huggingface.co/Hartunka/bert_base_km_5_v2) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1071
-- Pearson: 0.4559
-- Spearmanr: 0.4422
-- Combined Score: 0.4491
+- Loss: 1.8177
+- Pearson: 0.4729
+- Spearmanr: 0.4647
+- Combined Score: 0.4688
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 9.0,
+    "eval_combined_score": 0.4688225299634901,
+    "eval_loss": 1.817720890045166,
+    "eval_pearson": 0.4729149719474638,
+    "eval_runtime": 0.9764,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1536.307,
+    "eval_spearmanr": 0.4647300879795164,
+    "eval_steps_per_second": 6.145,
+    "total_flos": 6806753442049536.0,
+    "train_loss": 1.0066402430695611,
+    "train_runtime": 111.5858,
+    "train_samples": 5749,
+    "train_samples_per_second": 2576.044,
+    "train_steps_per_second": 10.306
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 9.0,
+    "eval_combined_score": 0.4688225299634901,
+    "eval_loss": 1.817720890045166,
+    "eval_pearson": 0.4729149719474638,
+    "eval_runtime": 0.9764,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1536.307,
+    "eval_spearmanr": 0.4647300879795164,
+    "eval_steps_per_second": 6.145
+}

logs/events.out.tfevents.1745274940.s_005_m.2836894.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8202f3a7f1b2914ae9279307f83548e40dfc21ace35d87f43211ae2b356be4e6
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.0,
+    "total_flos": 6806753442049536.0,
+    "train_loss": 1.0066402430695611,
+    "train_runtime": 111.5858,
+    "train_samples": 5749,
+    "train_samples_per_second": 2576.044,
+    "train_steps_per_second": 10.306
+}

trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_global_step": 92,
+  "best_metric": 1.817720890045166,
+  "best_model_checkpoint": "bert_base_km_5_v2_stsb/checkpoint-92",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 207,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.4511308670043945,
+      "learning_rate": 4.9e-05,
+      "loss": 2.6459,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.17748213508105598,
+      "eval_loss": 2.496568441390991,
+      "eval_pearson": 0.18348537128147316,
+      "eval_runtime": 0.9806,
+      "eval_samples_per_second": 1529.654,
+      "eval_spearmanr": 0.1714788988806388,
+      "eval_steps_per_second": 6.119,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.336346626281738,
+      "learning_rate": 4.8e-05,
+      "loss": 1.8235,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.3571596918178632,
+      "eval_loss": 2.291367769241333,
+      "eval_pearson": 0.359350055782331,
+      "eval_runtime": 0.966,
+      "eval_samples_per_second": 1552.716,
+      "eval_spearmanr": 0.3549693278533955,
+      "eval_steps_per_second": 6.211,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 16.716764450073242,
+      "learning_rate": 4.7e-05,
+      "loss": 1.4306,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.4254263499654776,
+      "eval_loss": 2.0514206886291504,
+      "eval_pearson": 0.42419705246176315,
+      "eval_runtime": 0.947,
+      "eval_samples_per_second": 1583.909,
+      "eval_spearmanr": 0.4266556474691921,
+      "eval_steps_per_second": 6.336,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 9.418330192565918,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.0154,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.4688225299634901,
+      "eval_loss": 1.817720890045166,
+      "eval_pearson": 0.4729149719474638,
+      "eval_runtime": 1.0262,
+      "eval_samples_per_second": 1461.68,
+      "eval_spearmanr": 0.4647300879795164,
+      "eval_steps_per_second": 5.847,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 10.213177680969238,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6595,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.4299374338757819,
+      "eval_loss": 2.1355791091918945,
+      "eval_pearson": 0.431103450256541,
+      "eval_runtime": 1.0013,
+      "eval_samples_per_second": 1498.103,
+      "eval_spearmanr": 0.42877141749502284,
+      "eval_steps_per_second": 5.992,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.467452049255371,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5214,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.4621440105497302,
+      "eval_loss": 2.0065433979034424,
+      "eval_pearson": 0.4627651439047887,
+      "eval_runtime": 1.0073,
+      "eval_samples_per_second": 1489.179,
+      "eval_spearmanr": 0.4615228771946718,
+      "eval_steps_per_second": 5.957,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.725819110870361,
+      "learning_rate": 4.3e-05,
+      "loss": 0.3787,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.44512872661303926,
+      "eval_loss": 2.222083806991577,
+      "eval_pearson": 0.44946999792264725,
+      "eval_runtime": 0.9699,
+      "eval_samples_per_second": 1546.573,
+      "eval_spearmanr": 0.44078745530343133,
+      "eval_steps_per_second": 6.186,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 8.177399635314941,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3169,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.4610558657175695,
+      "eval_loss": 2.1128690242767334,
+      "eval_pearson": 0.4651749975576446,
+      "eval_runtime": 1.0058,
+      "eval_samples_per_second": 1491.287,
+      "eval_spearmanr": 0.4569367338774944,
+      "eval_steps_per_second": 5.965,
+      "step": 184
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 6.235842704772949,
+      "learning_rate": 4.1e-05,
+      "loss": 0.2679,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "eval_combined_score": 0.44906447680245065,
+      "eval_loss": 2.1071338653564453,
+      "eval_pearson": 0.45592278289045723,
+      "eval_runtime": 0.9497,
+      "eval_samples_per_second": 1579.367,
+      "eval_spearmanr": 0.44220617071444407,
+      "eval_steps_per_second": 6.317,
+      "step": 207
+    },
+    {
+      "epoch": 9.0,
+      "step": 207,
+      "total_flos": 6806753442049536.0,
+      "train_loss": 1.0066402430695611,
+      "train_runtime": 111.5858,
+      "train_samples_per_second": 2576.044,
+      "train_steps_per_second": 10.306
+    }
+  ],
+  "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": 6806753442049536.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}