End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: distilbert_rand_100_v1_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8176354192431363
+    - name: F1
+      type: f1
+      value: 0.7602198445477901
 ---
 
 <!-- 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_100_v1_qqp
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_100_v1](https://huggingface.co/Hartunka/distilbert_rand_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_100_v1](https://huggingface.co/Hartunka/distilbert_rand_100_v1) on the GLUE QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5775
-- Accuracy: 0.8309
-- F1: 0.7785
-- Combined Score: 0.8047
+- Loss: 0.3936
+- Accuracy: 0.8176
+- F1: 0.7602
+- Combined Score: 0.7889
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8176354192431363,
+    "eval_combined_score": 0.7889276318954632,
+    "eval_f1": 0.7602198445477901,
+    "eval_loss": 0.3936457335948944,
+    "eval_runtime": 16.1889,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 2497.394,
+    "eval_steps_per_second": 9.76,
+    "total_flos": 1.686920659598684e+17,
+    "train_loss": 0.26570088311996903,
+    "train_runtime": 2420.2712,
+    "train_samples": 363846,
+    "train_samples_per_second": 7516.637,
+    "train_steps_per_second": 29.377
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.8176354192431363,
+    "eval_combined_score": 0.7889276318954632,
+    "eval_f1": 0.7602198445477901,
+    "eval_loss": 0.3936457335948944,
+    "eval_runtime": 16.1889,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 2497.394,
+    "eval_steps_per_second": 9.76
+}

logs/events.out.tfevents.1744946633.s_005_m.2758941.97

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00640dad4332562c3cec7c6164bbd134007c42eee5f90077d382af3e9415055
+size 467

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1.686920659598684e+17,
+    "train_loss": 0.26570088311996903,
+    "train_runtime": 2420.2712,
+    "train_samples": 363846,
+    "train_samples_per_second": 7516.637,
+    "train_steps_per_second": 29.377
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 2844,
+  "best_metric": 0.3936457335948944,
+  "best_model_checkpoint": "distilbert_rand_100_v1_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": 1.7591784000396729,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4785,
+      "step": 1422
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7908236458075686,
+      "eval_combined_score": 0.7345528431799664,
+      "eval_f1": 0.6782820405523643,
+      "eval_loss": 0.436032772064209,
+      "eval_runtime": 16.3318,
+      "eval_samples_per_second": 2475.543,
+      "eval_steps_per_second": 9.674,
+      "step": 1422
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.8016581535339355,
+      "learning_rate": 4.8e-05,
+      "loss": 0.3705,
+      "step": 2844
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8176354192431363,
+      "eval_combined_score": 0.7889276318954632,
+      "eval_f1": 0.7602198445477901,
+      "eval_loss": 0.3936457335948944,
+      "eval_runtime": 16.2709,
+      "eval_samples_per_second": 2484.805,
+      "eval_steps_per_second": 9.711,
+      "step": 2844
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.5234177112579346,
+      "learning_rate": 4.7e-05,
+      "loss": 0.2973,
+      "step": 4266
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8239673509769972,
+      "eval_combined_score": 0.7980132050019983,
+      "eval_f1": 0.7720590590269993,
+      "eval_loss": 0.403690367937088,
+      "eval_runtime": 16.2602,
+      "eval_samples_per_second": 2486.433,
+      "eval_steps_per_second": 9.717,
+      "step": 4266
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.370173931121826,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.2384,
+      "step": 5688
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8322532772693544,
+      "eval_combined_score": 0.7964977668361871,
+      "eval_f1": 0.7607422564030198,
+      "eval_loss": 0.4373086094856262,
+      "eval_runtime": 16.2418,
+      "eval_samples_per_second": 2489.253,
+      "eval_steps_per_second": 9.728,
+      "step": 5688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.989241361618042,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1915,
+      "step": 7110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8357160524363096,
+      "eval_combined_score": 0.8054341941260763,
+      "eval_f1": 0.775152335815843,
+      "eval_loss": 0.434268057346344,
+      "eval_runtime": 16.2081,
+      "eval_samples_per_second": 2494.43,
+      "eval_steps_per_second": 9.748,
+      "step": 7110
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.952167510986328,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1556,
+      "step": 8532
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8352213702696017,
+      "eval_combined_score": 0.8058846503860251,
+      "eval_f1": 0.7765479305024485,
+      "eval_loss": 0.5154929161071777,
+      "eval_runtime": 16.2597,
+      "eval_samples_per_second": 2486.519,
+      "eval_steps_per_second": 9.717,
+      "step": 8532
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.663344383239746,
+      "learning_rate": 4.3e-05,
+      "loss": 0.1281,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8309423695275785,
+      "eval_combined_score": 0.8047327122580377,
+      "eval_f1": 0.7785230549884968,
+      "eval_loss": 0.5775499939918518,
+      "eval_runtime": 16.2213,
+      "eval_samples_per_second": 2492.408,
+      "eval_steps_per_second": 9.74,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "step": 9954,
+      "total_flos": 1.686920659598684e+17,
+      "train_loss": 0.26570088311996903,
+      "train_runtime": 2420.2712,
+      "train_samples_per_second": 7516.637,
+      "train_steps_per_second": 29.377
+    }
+  ],
+  "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
+}