End of training

README.md

@@ -1,13 +1,28 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_5_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - spearmanr
 model-index:
 - name: distilbert_rand_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: 0.2724963061287522
 ---
 
 <!-- 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_v2_stsb
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_5_v2](https://huggingface.co/Hartunka/distilbert_rand_5_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_5_v2](https://huggingface.co/Hartunka/distilbert_rand_5_v2) on the GLUE STSB dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4665
-- Pearson: 0.3652
-- Spearmanr: 0.3618
-- Combined Score: 0.3635
+- Loss: 2.2658
+- Pearson: 0.2859
+- Spearmanr: 0.2725
+- Combined Score: 0.2792
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.27922213217540587,
+    "eval_loss": 2.2658326625823975,
+    "eval_pearson": 0.28594795822205954,
+    "eval_runtime": 0.6963,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2154.37,
+    "eval_spearmanr": 0.2724963061287522,
+    "eval_steps_per_second": 8.617,
+    "total_flos": 3046165974478848.0,
+    "train_loss": 1.2865250680757605,
+    "train_runtime": 58.9398,
+    "train_samples": 5749,
+    "train_samples_per_second": 4877.013,
+    "train_steps_per_second": 19.511
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_combined_score": 0.27922213217540587,
+    "eval_loss": 2.2658326625823975,
+    "eval_pearson": 0.28594795822205954,
+    "eval_runtime": 0.6963,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2154.37,
+    "eval_spearmanr": 0.2724963061287522,
+    "eval_steps_per_second": 8.617
+}

logs/events.out.tfevents.1745350097.s_005_m.2850345.103

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70096ab91881b1810c22cbf74f2fda269f10f210e5c522aad46139cc647fb23c
+size 473

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 3046165974478848.0,
+    "train_loss": 1.2865250680757605,
+    "train_runtime": 58.9398,
+    "train_samples": 5749,
+    "train_samples_per_second": 4877.013,
+    "train_steps_per_second": 19.511
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 69,
+  "best_metric": 2.2658326625823975,
+  "best_model_checkpoint": "distilbert_rand_5_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": 5.0608110427856445,
+      "learning_rate": 4.9e-05,
+      "loss": 2.6404,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.11699342039692526,
+      "eval_loss": 2.41465425491333,
+      "eval_pearson": 0.12565635781319812,
+      "eval_runtime": 0.6424,
+      "eval_samples_per_second": 2335.013,
+      "eval_spearmanr": 0.10833048298065238,
+      "eval_steps_per_second": 9.34,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.66240930557251,
+      "learning_rate": 4.8e-05,
+      "loss": 1.8953,
+      "step": 46
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.1914796307307736,
+      "eval_loss": 2.4776315689086914,
+      "eval_pearson": 0.20277521257509618,
+      "eval_runtime": 0.6517,
+      "eval_samples_per_second": 2301.755,
+      "eval_spearmanr": 0.180184048886451,
+      "eval_steps_per_second": 9.207,
+      "step": 46
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.03953218460083,
+      "learning_rate": 4.7e-05,
+      "loss": 1.6258,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.27922213217540587,
+      "eval_loss": 2.2658326625823975,
+      "eval_pearson": 0.28594795822205954,
+      "eval_runtime": 0.6249,
+      "eval_samples_per_second": 2400.384,
+      "eval_spearmanr": 0.2724963061287522,
+      "eval_steps_per_second": 9.602,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 9.639275550842285,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.3145,
+      "step": 92
+    },
+    {
+      "epoch": 4.0,
+      "eval_combined_score": 0.32255239461739416,
+      "eval_loss": 2.3222312927246094,
+      "eval_pearson": 0.3224380385194155,
+      "eval_runtime": 0.6167,
+      "eval_samples_per_second": 2432.496,
+      "eval_spearmanr": 0.3226667507153729,
+      "eval_steps_per_second": 9.73,
+      "step": 92
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 10.404162406921387,
+      "learning_rate": 4.5e-05,
+      "loss": 0.9743,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_combined_score": 0.317422126291488,
+      "eval_loss": 2.4189276695251465,
+      "eval_pearson": 0.3225324801153353,
+      "eval_runtime": 0.6533,
+      "eval_samples_per_second": 2295.945,
+      "eval_spearmanr": 0.3123117724676408,
+      "eval_steps_per_second": 9.184,
+      "step": 115
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 12.562041282653809,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.7528,
+      "step": 138
+    },
+    {
+      "epoch": 6.0,
+      "eval_combined_score": 0.3305215504599094,
+      "eval_loss": 2.4691739082336426,
+      "eval_pearson": 0.33259118628799356,
+      "eval_runtime": 0.6654,
+      "eval_samples_per_second": 2254.382,
+      "eval_spearmanr": 0.3284519146318252,
+      "eval_steps_per_second": 9.018,
+      "step": 138
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 9.112942695617676,
+      "learning_rate": 4.3e-05,
+      "loss": 0.5989,
+      "step": 161
+    },
+    {
+      "epoch": 7.0,
+      "eval_combined_score": 0.360745901774201,
+      "eval_loss": 2.382098436355591,
+      "eval_pearson": 0.36246744992255747,
+      "eval_runtime": 0.6361,
+      "eval_samples_per_second": 2358.195,
+      "eval_spearmanr": 0.35902435362584456,
+      "eval_steps_per_second": 9.433,
+      "step": 161
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 23.918201446533203,
+      "learning_rate": 4.2e-05,
+      "loss": 0.4902,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "eval_combined_score": 0.36350579676169986,
+      "eval_loss": 2.4664862155914307,
+      "eval_pearson": 0.36518619089227783,
+      "eval_runtime": 0.6496,
+      "eval_samples_per_second": 2309.002,
+      "eval_spearmanr": 0.3618254026311219,
+      "eval_steps_per_second": 9.236,
+      "step": 184
+    },
+    {
+      "epoch": 8.0,
+      "step": 184,
+      "total_flos": 3046165974478848.0,
+      "train_loss": 1.2865250680757605,
+      "train_runtime": 58.9398,
+      "train_samples_per_second": 4877.013,
+      "train_steps_per_second": 19.511
+    }
+  ],
+  "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
+}