End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: tiny_bert_rand_50_v1_cola
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE COLA
+      type: glue
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,11 +33,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_50_v1_cola
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v1](https://huggingface.co/Hartunka/tiny_bert_rand_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v1](https://huggingface.co/Hartunka/tiny_bert_rand_50_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7260
-- Matthews Correlation: 0.0758
-- Accuracy: 0.6222
+- Loss: 0.6171
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6171163320541382,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.4905,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2126.307,
+    "eval_steps_per_second": 10.193,
+    "total_flos": 1345426898614272.0,
+    "train_loss": 0.5469665293600044,
+    "train_runtime": 42.0475,
+    "train_samples": 8551,
+    "train_samples_per_second": 10168.271,
+    "train_steps_per_second": 40.43
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.6171163320541382,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.4905,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2126.307,
+    "eval_steps_per_second": 10.193
+}

logs/events.out.tfevents.1744824182.s_004_m

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f58b90f86be80d7bba4200f3541df0138def2bb95ed42987b021a85e829dd28
+size 40

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 1345426898614272.0,
+    "train_loss": 0.5469665293600044,
+    "train_runtime": 42.0475,
+    "train_samples": 8551,
+    "train_samples_per_second": 10168.271,
+    "train_steps_per_second": 40.43
+}

trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_metric": 0.6171163320541382,
+  "best_model_checkpoint": "tiny_bert_rand_50_v1_cola/checkpoint-34",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7138214111328125,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6134,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6171163320541382,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4916,
+      "eval_samples_per_second": 2121.452,
+      "eval_steps_per_second": 10.17,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9771915078163147,
+      "learning_rate": 4.8e-05,
+      "loss": 0.601,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6195900440216064,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3924,
+      "eval_samples_per_second": 2657.785,
+      "eval_steps_per_second": 12.741,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1553252935409546,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5781,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6259943246841431,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.3832,
+      "eval_samples_per_second": 2721.81,
+      "eval_steps_per_second": 13.048,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9693224430084229,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5374,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6836050152778625,
+      "eval_loss": 0.6578595042228699,
+      "eval_matthews_correlation": 0.042582902474918326,
+      "eval_runtime": 0.3804,
+      "eval_samples_per_second": 2741.559,
+      "eval_steps_per_second": 13.143,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.186906337738037,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4953,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6538830399513245,
+      "eval_loss": 0.6752046942710876,
+      "eval_matthews_correlation": 0.08801919690309869,
+      "eval_runtime": 0.3951,
+      "eval_samples_per_second": 2640.126,
+      "eval_steps_per_second": 12.656,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.2683961391448975,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.4567,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6222435235977173,
+      "eval_loss": 0.7260271310806274,
+      "eval_matthews_correlation": 0.07575741604681904,
+      "eval_runtime": 0.4037,
+      "eval_samples_per_second": 2583.494,
+      "eval_steps_per_second": 12.385,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "step": 204,
+      "total_flos": 1345426898614272.0,
+      "train_loss": 0.5469665293600044,
+      "train_runtime": 42.0475,
+      "train_samples_per_second": 10168.271,
+      "train_steps_per_second": 40.43
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 1345426898614272.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}