End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_5_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: distilbert_rand_5_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: 0.30225387805423815
 ---
 
 <!-- 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_5_v1_stsb
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_5_v1](https://huggingface.co/Hartunka/distilbert_rand_5_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_5_v1](https://huggingface.co/Hartunka/distilbert_rand_5_v1) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3035
-- Pearson: 0.3740
-- Spearmanr: 0.3674
-- Combined Score: 0.3707
+- Loss: 2.1528
+- Pearson: 0.3145
+- Spearmanr: 0.3023
+- Combined Score: 0.3084
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.30836011830151533,
+    "eval_loss": 2.152787208557129,
+    "eval_pearson": 0.3144663585487925,
+    "eval_runtime": 0.6387,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2348.471,
+    "eval_spearmanr": 0.30225387805423815,
+    "eval_steps_per_second": 9.394,
+    "total_flos": 3046165974478848.0,
+    "train_loss": 1.2547789812088013,
+    "train_runtime": 57.2922,
+    "train_samples": 5749,
+    "train_samples_per_second": 5017.259,
+    "train_steps_per_second": 20.073
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.30836011830151533,
+    "eval_loss": 2.152787208557129,
+    "eval_pearson": 0.3144663585487925,
+    "eval_runtime": 0.6387,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2348.471,
+    "eval_spearmanr": 0.30225387805423815,
+    "eval_steps_per_second": 9.394
+}

logs/events.out.tfevents.1744916409.s_005_m.2758941.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc537bf95cce23a6e06419a0a53d90ec3a32989cdf3df61ce8aa4c7b2615423
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 3046165974478848.0,
+    "train_loss": 1.2547789812088013,
+    "train_runtime": 57.2922,
+    "train_samples": 5749,
+    "train_samples_per_second": 5017.259,
+    "train_steps_per_second": 20.073
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 69,
+  "best_metric": 2.152787208557129,
+  "best_model_checkpoint": "distilbert_rand_5_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": 5.257723331451416,
+      "learning_rate": 4.9e-05,
+      "loss": 2.5973,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.12685381354093894,
+      "eval_loss": 2.4120709896087646,
+      "eval_pearson": 0.13508782894311455,
+      "eval_runtime": 0.6223,
+      "eval_samples_per_second": 2410.302,
+      "eval_spearmanr": 0.11861979813876336,
+      "eval_steps_per_second": 9.641,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.574005126953125,
+      "learning_rate": 4.8e-05,
+      "loss": 1.9068,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.1879283466033767,
+      "eval_loss": 2.3606996536254883,
+      "eval_pearson": 0.1995929275739006,
+      "eval_runtime": 0.6528,
+      "eval_samples_per_second": 2297.884,
+      "eval_spearmanr": 0.17626376563285284,
+      "eval_steps_per_second": 9.192,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.735135555267334,
+      "learning_rate": 4.7e-05,
+      "loss": 1.6159,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.30836011830151533,
+      "eval_loss": 2.152787208557129,
+      "eval_pearson": 0.3144663585487925,
+      "eval_runtime": 0.6597,
+      "eval_samples_per_second": 2273.669,
+      "eval_spearmanr": 0.30225387805423815,
+      "eval_steps_per_second": 9.095,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.913302421569824,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.2787,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.3297024531434931,
+      "eval_loss": 2.2168540954589844,
+      "eval_pearson": 0.33387930176325886,
+      "eval_runtime": 0.6261,
+      "eval_samples_per_second": 2395.944,
+      "eval_spearmanr": 0.32552560452372736,
+      "eval_steps_per_second": 9.584,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 10.499592781066895,
+      "learning_rate": 4.5e-05,
+      "loss": 0.9322,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.3411050735284236,
+      "eval_loss": 2.3111720085144043,
+      "eval_pearson": 0.34477417705044855,
+      "eval_runtime": 0.6133,
+      "eval_samples_per_second": 2445.669,
+      "eval_spearmanr": 0.3374359700063987,
+      "eval_steps_per_second": 9.783,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 9.493566513061523,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.7176,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.3320775058651253,
+      "eval_loss": 2.495030641555786,
+      "eval_pearson": 0.33614766062651785,
+      "eval_runtime": 0.6572,
+      "eval_samples_per_second": 2282.427,
+      "eval_spearmanr": 0.3280073511037327,
+      "eval_steps_per_second": 9.13,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.682682991027832,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5481,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.36052540541106903,
+      "eval_loss": 2.5333147048950195,
+      "eval_pearson": 0.3626376958035924,
+      "eval_runtime": 0.6439,
+      "eval_samples_per_second": 2329.629,
+      "eval_spearmanr": 0.3584131150185456,
+      "eval_steps_per_second": 9.319,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 14.030130386352539,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4417,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.3707102028268629,
+      "eval_loss": 2.3035025596618652,
+      "eval_pearson": 0.3740364690553659,
+      "eval_runtime": 0.6182,
+      "eval_samples_per_second": 2426.515,
+      "eval_spearmanr": 0.3673839365983599,
+      "eval_steps_per_second": 9.706,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "step": 184,
+      "total_flos": 3046165974478848.0,
+      "train_loss": 1.2547789812088013,
+      "train_runtime": 57.2922,
+      "train_samples_per_second": 5017.259,
+      "train_steps_per_second": 20.073
+    }
+  ],
+  "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
+}