End of training

README.md

@@ -1,14 +1,32 @@
 ---
 library_name: transformers
+language:
+- en
 base_model: Hartunka/distilbert_rand_100_v2
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: distilbert_rand_100_v2_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6936274509803921
+    - name: F1
+      type: f1
+      value: 0.7974068071312804
 ---
 
 <!-- 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_v2_mrpc
 
-This model is a fine-tuned version of [Hartunka/distilbert_rand_100_v2](https://huggingface.co/Hartunka/distilbert_rand_100_v2) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/distilbert_rand_100_v2](https://huggingface.co/Hartunka/distilbert_rand_100_v2) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4994
-- Accuracy: 0.6324
-- F1: 0.7082
-- Combined Score: 0.6703
+- Loss: 0.5903
+- Accuracy: 0.6936
+- F1: 0.7974
+- Combined Score: 0.7455
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6936274509803921,
+    "eval_combined_score": 0.7455171290558362,
+    "eval_f1": 0.7974068071312804,
+    "eval_loss": 0.5903356075286865,
+    "eval_runtime": 0.2336,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1746.628,
+    "eval_steps_per_second": 8.562,
+    "total_flos": 1700616463945728.0,
+    "train_loss": 0.37518059753236316,
+    "train_runtime": 35.659,
+    "train_samples": 3668,
+    "train_samples_per_second": 5143.168,
+    "train_steps_per_second": 21.033
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6936274509803921,
+    "eval_combined_score": 0.7455171290558362,
+    "eval_f1": 0.7974068071312804,
+    "eval_loss": 0.5903356075286865,
+    "eval_runtime": 0.2336,
+    "eval_samples": 408,
+    "eval_samples_per_second": 1746.628,
+    "eval_steps_per_second": 8.562
+}

logs/events.out.tfevents.1745376055.s_005_m.2850345.165

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70386a6a978e731f1bd4fc4b49bfd7c7171f780582f51391b999413a68890ec8
+size 459

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 1700616463945728.0,
+    "train_loss": 0.37518059753236316,
+    "train_runtime": 35.659,
+    "train_samples": 3668,
+    "train_samples_per_second": 5143.168,
+    "train_steps_per_second": 21.033
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 30,
+  "best_metric": 0.5903356075286865,
+  "best_model_checkpoint": "distilbert_rand_100_v2_mrpc/checkpoint-30",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0330828428268433,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6269,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6715686274509803,
+      "eval_combined_score": 0.7233682063429399,
+      "eval_f1": 0.7751677852348994,
+      "eval_loss": 0.6201698184013367,
+      "eval_runtime": 0.1839,
+      "eval_samples_per_second": 2218.432,
+      "eval_steps_per_second": 10.875,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.89597749710083,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5818,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6936274509803921,
+      "eval_combined_score": 0.7455171290558362,
+      "eval_f1": 0.7974068071312804,
+      "eval_loss": 0.5903356075286865,
+      "eval_runtime": 0.1963,
+      "eval_samples_per_second": 2078.792,
+      "eval_steps_per_second": 10.19,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.313245415687561,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5151,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6887254901960784,
+      "eval_combined_score": 0.7407738380833573,
+      "eval_f1": 0.7928221859706363,
+      "eval_loss": 0.608057975769043,
+      "eval_runtime": 0.1891,
+      "eval_samples_per_second": 2157.874,
+      "eval_steps_per_second": 10.578,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.2981903553009033,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.412,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6446078431372549,
+      "eval_combined_score": 0.685252881871085,
+      "eval_f1": 0.725897920604915,
+      "eval_loss": 0.7462877035140991,
+      "eval_runtime": 0.2071,
+      "eval_samples_per_second": 1970.02,
+      "eval_steps_per_second": 9.657,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.860208749771118,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2566,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6372549019607843,
+      "eval_combined_score": 0.678475935828877,
+      "eval_f1": 0.7196969696969697,
+      "eval_loss": 1.0278682708740234,
+      "eval_runtime": 0.1825,
+      "eval_samples_per_second": 2235.714,
+      "eval_steps_per_second": 10.959,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.500450372695923,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1435,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6495098039215687,
+      "eval_combined_score": 0.6911100421477002,
+      "eval_f1": 0.7327102803738318,
+      "eval_loss": 1.291999101638794,
+      "eval_runtime": 0.1923,
+      "eval_samples_per_second": 2121.965,
+      "eval_steps_per_second": 10.402,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.059184551239014,
+      "learning_rate": 4.3e-05,
+      "loss": 0.0905,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6323529411764706,
+      "eval_combined_score": 0.6702620737010758,
+      "eval_f1": 0.708171206225681,
+      "eval_loss": 1.4994282722473145,
+      "eval_runtime": 0.2107,
+      "eval_samples_per_second": 1936.26,
+      "eval_steps_per_second": 9.491,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 1700616463945728.0,
+      "train_loss": 0.37518059753236316,
+      "train_runtime": 35.659,
+      "train_samples_per_second": 5143.168,
+      "train_steps_per_second": 21.033
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "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": 1700616463945728.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}