End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_100_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 - f1
 model-index:
 - name: tiny_bert_rand_100_v1_mrpc
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6985294117647058
+    - name: F1
+      type: f1
+      value: 0.8050713153724247
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,12 +33,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_100_v1_mrpc
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v1](https://huggingface.co/Hartunka/tiny_bert_rand_100_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v1](https://huggingface.co/Hartunka/tiny_bert_rand_100_v1) on the GLUE MRPC dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9900
-- Accuracy: 0.6446
-- F1: 0.7330
-- Combined Score: 0.6888
+- Loss: 0.5959
+- Accuracy: 0.6985
+- F1: 0.8051
+- Combined Score: 0.7518
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6985294117647058,
+    "eval_combined_score": 0.7518003635685653,
+    "eval_f1": 0.8050713153724247,
+    "eval_loss": 0.5958610773086548,
+    "eval_runtime": 0.1853,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2202.176,
+    "eval_steps_per_second": 10.795,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.46518308548700243,
+    "train_runtime": 24.1609,
+    "train_samples": 3668,
+    "train_samples_per_second": 7590.788,
+    "train_steps_per_second": 31.042
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.6985294117647058,
+    "eval_combined_score": 0.7518003635685653,
+    "eval_f1": 0.8050713153724247,
+    "eval_loss": 0.5958610773086548,
+    "eval_runtime": 0.1853,
+    "eval_samples": 408,
+    "eval_samples_per_second": 2202.176,
+    "eval_steps_per_second": 10.795
+}

logs/events.out.tfevents.1744830194.s_004_m

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b5a085874cd3e70613c6b98ac23ed14941db120a921976281da9427067fc93
+size 351

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.0,
+    "total_flos": 673316591603712.0,
+    "train_loss": 0.46518308548700243,
+    "train_runtime": 24.1609,
+    "train_samples": 3668,
+    "train_samples_per_second": 7590.788,
+    "train_steps_per_second": 31.042
+}

trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": 0.5958610773086548,
+  "best_model_checkpoint": "tiny_bert_rand_100_v1_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": 0.6730923652648926,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6273,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6887254901960784,
+      "eval_combined_score": 0.7456069130607141,
+      "eval_f1": 0.80248833592535,
+      "eval_loss": 0.6086593270301819,
+      "eval_runtime": 0.2031,
+      "eval_samples_per_second": 2009.033,
+      "eval_steps_per_second": 9.848,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3474140167236328,
+      "learning_rate": 4.8e-05,
+      "loss": 0.5923,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6985294117647058,
+      "eval_combined_score": 0.7518003635685653,
+      "eval_f1": 0.8050713153724247,
+      "eval_loss": 0.5958610773086548,
+      "eval_runtime": 0.1692,
+      "eval_samples_per_second": 2411.212,
+      "eval_steps_per_second": 11.82,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0300101041793823,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5507,
+      "step": 45
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_combined_score": 0.7583039524958248,
+      "eval_f1": 0.8107255520504731,
+      "eval_loss": 0.6265156865119934,
+      "eval_runtime": 0.173,
+      "eval_samples_per_second": 2358.244,
+      "eval_steps_per_second": 11.56,
+      "step": 45
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.557811975479126,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5072,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6151960784313726,
+      "eval_combined_score": 0.6515344209254279,
+      "eval_f1": 0.6878727634194831,
+      "eval_loss": 0.6902447938919067,
+      "eval_runtime": 0.1921,
+      "eval_samples_per_second": 2124.115,
+      "eval_steps_per_second": 10.412,
+      "step": 60
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.892411708831787,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4237,
+      "step": 75
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_combined_score": 0.7096969696969697,
+      "eval_f1": 0.7527272727272727,
+      "eval_loss": 0.7021771669387817,
+      "eval_runtime": 0.1952,
+      "eval_samples_per_second": 2090.494,
+      "eval_steps_per_second": 10.248,
+      "step": 75
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.483872413635254,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.3165,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6446078431372549,
+      "eval_combined_score": 0.6867899028770387,
+      "eval_f1": 0.7289719626168224,
+      "eval_loss": 0.8693117499351501,
+      "eval_runtime": 0.1787,
+      "eval_samples_per_second": 2282.691,
+      "eval_steps_per_second": 11.19,
+      "step": 90
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.6365251541137695,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2385,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6446078431372549,
+      "eval_combined_score": 0.688786426172679,
+      "eval_f1": 0.7329650092081031,
+      "eval_loss": 0.9899513125419617,
+      "eval_runtime": 0.1918,
+      "eval_samples_per_second": 2127.706,
+      "eval_steps_per_second": 10.43,
+      "step": 105
+    },
+    {
+      "epoch": 7.0,
+      "step": 105,
+      "total_flos": 673316591603712.0,
+      "train_loss": 0.46518308548700243,
+      "train_runtime": 24.1609,
+      "train_samples_per_second": 7590.788,
+      "train_steps_per_second": 31.042
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 673316591603712.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}