End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_50_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: distilbert_rand_50_v2_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8168191936680682
+    - name: F1
+      type: f1
+      value: 0.7451479697178252
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert_rand_50_v2_qqp
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_50_v2](https://huggingface.co/Hartunka/distilbert_rand_50_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_50_v2](https://huggingface.co/Hartunka/distilbert_rand_50_v2) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5227
-- Accuracy: 0.8370
-- F1: 0.7826
-- Combined Score: 0.8098
+- Loss: 0.3923
+- Accuracy: 0.8168
+- F1: 0.7451
+- Combined Score: 0.7810
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8168191936680682,
+    "eval_combined_score": 0.7809835816929467,
+    "eval_f1": 0.7451479697178252,
+    "eval_loss": 0.39231884479522705,
+    "eval_runtime": 16.3135,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 2478.313,
+    "eval_steps_per_second": 9.685,
+    "total_flos": 1.686920659598684e+17,
+    "train_loss": 0.2670506727798459,
+    "train_runtime": 2422.7615,
+    "train_samples": 363846,
+    "train_samples_per_second": 7508.911,
+    "train_steps_per_second": 29.347
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8168191936680682,
+    "eval_combined_score": 0.7809835816929467,
+    "eval_f1": 0.7451479697178252,
+    "eval_loss": 0.39231884479522705,
+    "eval_runtime": 16.3135,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 2478.313,
+    "eval_steps_per_second": 9.685
+}

logs/events.out.tfevents.1745371976.s_005_m.2850345.151

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5866555ea07ef3e69dd444cb0d17c3fb054bcae3663f6dbedc4884c29f8c1a9
+size 467

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1.686920659598684e+17,
+    "train_loss": 0.2670506727798459,
+    "train_runtime": 2422.7615,
+    "train_samples": 363846,
+    "train_samples_per_second": 7508.911,
+    "train_steps_per_second": 29.347
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 2844,
+  "best_metric": 0.39231884479522705,
+  "best_model_checkpoint": "distilbert_rand_50_v2_qqp/checkpoint-2844",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 9954,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.2142386436462402,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4752,
+      "step": 1422
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7852832055404403,
+      "eval_combined_score": 0.7193473958791753,
+      "eval_f1": 0.6534115862179103,
+      "eval_loss": 0.4499146044254303,
+      "eval_runtime": 16.5358,
+      "eval_samples_per_second": 2445.0,
+      "eval_steps_per_second": 9.555,
+      "step": 1422
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.8298840522766113,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3679,
+      "step": 2844
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8168191936680682,
+      "eval_combined_score": 0.7809835816929467,
+      "eval_f1": 0.7451479697178252,
+      "eval_loss": 0.39231884479522705,
+      "eval_runtime": 16.2933,
+      "eval_samples_per_second": 2481.394,
+      "eval_steps_per_second": 9.697,
+      "step": 2844
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.5703165531158447,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2972,
+      "step": 4266
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.826391293593866,
+      "eval_combined_score": 0.7968907586444889,
+      "eval_f1": 0.7673902236951119,
+      "eval_loss": 0.4010921120643616,
+      "eval_runtime": 16.2726,
+      "eval_samples_per_second": 2484.548,
+      "eval_steps_per_second": 9.71,
+      "step": 4266
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.0508337020874023,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2404,
+      "step": 5688
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8300766757358398,
+      "eval_combined_score": 0.7909863335342254,
+      "eval_f1": 0.7518959913326111,
+      "eval_loss": 0.44213730096817017,
+      "eval_runtime": 16.3021,
+      "eval_samples_per_second": 2480.053,
+      "eval_steps_per_second": 9.692,
+      "step": 5688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.1139888763427734,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1957,
+      "step": 7110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8347266881028939,
+      "eval_combined_score": 0.7990727336563188,
+      "eval_f1": 0.7634187792097437,
+      "eval_loss": 0.4787127375602722,
+      "eval_runtime": 16.2232,
+      "eval_samples_per_second": 2492.114,
+      "eval_steps_per_second": 9.739,
+      "step": 7110
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.34266996383667,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1604,
+      "step": 8532
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8346030175612169,
+      "eval_combined_score": 0.8022108062230373,
+      "eval_f1": 0.7698185948848577,
+      "eval_loss": 0.49750494956970215,
+      "eval_runtime": 16.266,
+      "eval_samples_per_second": 2485.556,
+      "eval_steps_per_second": 9.714,
+      "step": 8532
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.350759506225586,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1326,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8370269601780855,
+      "eval_combined_score": 0.809802046332237,
+      "eval_f1": 0.7825771324863884,
+      "eval_loss": 0.5226749181747437,
+      "eval_runtime": 16.3553,
+      "eval_samples_per_second": 2471.984,
+      "eval_steps_per_second": 9.66,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "step": 9954,
+      "total_flos": 1.686920659598684e+17,
+      "train_loss": 0.2670506727798459,
+      "train_runtime": 2422.7615,
+      "train_samples_per_second": 7508.911,
+      "train_steps_per_second": 29.347
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 71100,
+  "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": 1.686920659598684e+17,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}