End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_10_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: distilbert_rand_10_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: 0.3015093929726957
 ---
 
 <!-- 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_rand_10_v2_stsb
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_10_v2](https://huggingface.co/Hartunka/distilbert_rand_10_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_10_v2](https://huggingface.co/Hartunka/distilbert_rand_10_v2) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5305
-- Pearson: 0.3544
-- Spearmanr: 0.3537
-- Combined Score: 0.3541
+- Loss: 2.2101
+- Pearson: 0.3094
+- Spearmanr: 0.3015
+- Combined Score: 0.3055
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.30545924867679564,
+    "eval_loss": 2.2101211547851562,
+    "eval_pearson": 0.3094091043808956,
+    "eval_runtime": 0.639,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2347.4,
+    "eval_spearmanr": 0.3015093929726957,
+    "eval_steps_per_second": 9.39,
+    "total_flos": 3046165974478848.0,
+    "train_loss": 1.2931229135264521,
+    "train_runtime": 58.4889,
+    "train_samples": 5749,
+    "train_samples_per_second": 4914.604,
+    "train_steps_per_second": 19.662
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.30545924867679564,
+    "eval_loss": 2.2101211547851562,
+    "eval_pearson": 0.3094091043808956,
+    "eval_runtime": 0.639,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2347.4,
+    "eval_spearmanr": 0.3015093929726957,
+    "eval_steps_per_second": 9.39
+}

logs/events.out.tfevents.1745357827.s_005_m.2850345.121

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b47ee2aace521ac0f92a920360a31bd33c0e627957a376f796ff72e77d316a
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 3046165974478848.0,
+    "train_loss": 1.2931229135264521,
+    "train_runtime": 58.4889,
+    "train_samples": 5749,
+    "train_samples_per_second": 4914.604,
+    "train_steps_per_second": 19.662
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 69,
+  "best_metric": 2.2101211547851562,
+  "best_model_checkpoint": "distilbert_rand_10_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": 8.412630081176758,
+      "learning_rate": 4.9e-05,
+      "loss": 2.7267,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.11730191796661976,
+      "eval_loss": 2.4801809787750244,
+      "eval_pearson": 0.12599947329463,
+      "eval_runtime": 0.6218,
+      "eval_samples_per_second": 2412.241,
+      "eval_spearmanr": 0.10860436263860952,
+      "eval_steps_per_second": 9.649,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.434743404388428,
+      "learning_rate": 4.8e-05,
+      "loss": 1.9118,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.2198145239190804,
+      "eval_loss": 2.4210996627807617,
+      "eval_pearson": 0.22858826104692373,
+      "eval_runtime": 0.6616,
+      "eval_samples_per_second": 2267.335,
+      "eval_spearmanr": 0.21104078679123708,
+      "eval_steps_per_second": 9.069,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.30825424194336,
+      "learning_rate": 4.7e-05,
+      "loss": 1.6277,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.30545924867679564,
+      "eval_loss": 2.2101211547851562,
+      "eval_pearson": 0.3094091043808956,
+      "eval_runtime": 0.6458,
+      "eval_samples_per_second": 2322.606,
+      "eval_spearmanr": 0.3015093929726957,
+      "eval_steps_per_second": 9.29,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 9.640958786010742,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.3088,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.3061512586321524,
+      "eval_loss": 2.270442485809326,
+      "eval_pearson": 0.30733196515210104,
+      "eval_runtime": 0.6557,
+      "eval_samples_per_second": 2287.781,
+      "eval_spearmanr": 0.3049705521122038,
+      "eval_steps_per_second": 9.151,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 11.77796459197998,
+      "learning_rate": 4.5e-05,
+      "loss": 1.0113,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.3213830873754268,
+      "eval_loss": 2.440420627593994,
+      "eval_pearson": 0.3233004283304278,
+      "eval_runtime": 0.6643,
+      "eval_samples_per_second": 2258.15,
+      "eval_spearmanr": 0.3194657464204258,
+      "eval_steps_per_second": 9.033,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 8.813213348388672,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.7442,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.37704813229709916,
+      "eval_loss": 2.2810983657836914,
+      "eval_pearson": 0.37660572827228594,
+      "eval_runtime": 0.625,
+      "eval_samples_per_second": 2400.143,
+      "eval_spearmanr": 0.3774905363219124,
+      "eval_steps_per_second": 9.601,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 9.290400505065918,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5763,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.3448508484037617,
+      "eval_loss": 2.3778023719787598,
+      "eval_pearson": 0.34484885492343176,
+      "eval_runtime": 0.6503,
+      "eval_samples_per_second": 2306.606,
+      "eval_spearmanr": 0.3448528418840916,
+      "eval_steps_per_second": 9.226,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 5.34546422958374,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4382,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.3540750602041761,
+      "eval_loss": 2.530513286590576,
+      "eval_pearson": 0.3544031587599974,
+      "eval_runtime": 0.6397,
+      "eval_samples_per_second": 2344.97,
+      "eval_spearmanr": 0.35374696164835484,
+      "eval_steps_per_second": 9.38,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "step": 184,
+      "total_flos": 3046165974478848.0,
+      "train_loss": 1.2931229135264521,
+      "train_runtime": 58.4889,
+      "train_samples_per_second": 4914.604,
+      "train_steps_per_second": 19.662
+    }
+  ],
+  "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": 3046165974478848.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}