End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_km_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: distilbert_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: 0.19307206409980063
 ---
 
 <!-- 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. -->
 
 # distilbert_km_50_v1_stsb
 
-This model is a fine-tuned version of [Hartunka/distilbert_km_50_v1](https://huggingface.co/Hartunka/distilbert_km_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_km_50_v1](https://huggingface.co/Hartunka/distilbert_km_50_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5094
-- Pearson: 0.2699
-- Spearmanr: 0.2661
-- Combined Score: 0.2680
+- Loss: 2.1755
+- Pearson: 0.2112
+- Spearmanr: 0.1931
+- Combined Score: 0.2021
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 6.0,
+    "eval_combined_score": 0.20212342186544494,
+    "eval_loss": 2.175532579421997,
+    "eval_pearson": 0.21117477963108924,
+    "eval_runtime": 0.6245,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2402.019,
+    "eval_spearmanr": 0.19307206409980063,
+    "eval_steps_per_second": 9.608,
+    "total_flos": 2284624480859136.0,
+    "train_loss": 1.7693035015161487,
+    "train_runtime": 43.6785,
+    "train_samples": 5749,
+    "train_samples_per_second": 6581.04,
+    "train_steps_per_second": 26.329
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 6.0,
+    "eval_combined_score": 0.20212342186544494,
+    "eval_loss": 2.175532579421997,
+    "eval_pearson": 0.21117477963108924,
+    "eval_runtime": 0.6245,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2402.019,
+    "eval_spearmanr": 0.19307206409980063,
+    "eval_steps_per_second": 9.608
+}

logs/events.out.tfevents.1744690281.s_005_m.602156.67

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad428a6c49778074bda81fa7237a16467b40b071ccca62a263271fe2c9961f7
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 2284624480859136.0,
+    "train_loss": 1.7693035015161487,
+    "train_runtime": 43.6785,
+    "train_samples": 5749,
+    "train_samples_per_second": 6581.04,
+    "train_steps_per_second": 26.329
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_global_step": 23,
+  "best_metric": 2.175532579421997,
+  "best_model_checkpoint": "distilbert_km_50_v1_stsb/checkpoint-23",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 138,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.129865884780884,
+      "learning_rate": 4.9e-05,
+      "loss": 3.0505,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.20212342186544494,
+      "eval_loss": 2.175532579421997,
+      "eval_pearson": 0.21117477963108924,
+      "eval_runtime": 0.6434,
+      "eval_samples_per_second": 2331.437,
+      "eval_spearmanr": 0.19307206409980063,
+      "eval_steps_per_second": 9.326,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.838581085205078,
+      "learning_rate": 4.8e-05,
+      "loss": 2.0219,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.20676828858959528,
+      "eval_loss": 2.3759779930114746,
+      "eval_pearson": 0.21257932784860267,
+      "eval_runtime": 0.6551,
+      "eval_samples_per_second": 2289.665,
+      "eval_spearmanr": 0.20095724933058787,
+      "eval_steps_per_second": 9.159,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.249078750610352,
+      "learning_rate": 4.7e-05,
+      "loss": 1.7916,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.27639165228058654,
+      "eval_loss": 2.191002130508423,
+      "eval_pearson": 0.2832089343264203,
+      "eval_runtime": 0.6537,
+      "eval_samples_per_second": 2294.565,
+      "eval_spearmanr": 0.2695743702347528,
+      "eval_steps_per_second": 9.178,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.90875244140625,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.57,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.2651808793758065,
+      "eval_loss": 2.5241341590881348,
+      "eval_pearson": 0.2673137887479519,
+      "eval_runtime": 0.6237,
+      "eval_samples_per_second": 2405.091,
+      "eval_spearmanr": 0.2630479700036611,
+      "eval_steps_per_second": 9.62,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.098377227783203,
+      "learning_rate": 4.5e-05,
+      "loss": 1.2276,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.30398949048599433,
+      "eval_loss": 2.3850808143615723,
+      "eval_pearson": 0.3014914996634345,
+      "eval_runtime": 0.662,
+      "eval_samples_per_second": 2266.019,
+      "eval_spearmanr": 0.3064874813085541,
+      "eval_steps_per_second": 9.064,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 8.980904579162598,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.9544,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.2680040803079917,
+      "eval_loss": 2.5093834400177,
+      "eval_pearson": 0.26992062220843577,
+      "eval_runtime": 0.6455,
+      "eval_samples_per_second": 2323.845,
+      "eval_spearmanr": 0.2660875384075477,
+      "eval_steps_per_second": 9.295,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "step": 138,
+      "total_flos": 2284624480859136.0,
+      "train_loss": 1.7693035015161487,
+      "train_runtime": 43.6785,
+      "train_samples_per_second": 6581.04,
+      "train_steps_per_second": 26.329
+    }
+  ],
+  "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": 2284624480859136.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}