End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
 base_model: Hartunka/tiny_bert_km_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - matthews_correlation
 - accuracy
 model-index:
 - name: tiny_bert_km_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_km_50_v1_cola
 
-This model is a fine-tuned version of [Hartunka/tiny_bert_km_50_v1](https://huggingface.co/Hartunka/tiny_bert_km_50_v1) on an unknown dataset.
+This model is a fine-tuned version of [Hartunka/tiny_bert_km_50_v1](https://huggingface.co/Hartunka/tiny_bert_km_50_v1) on the GLUE COLA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6700
-- Matthews Correlation: 0.1136
-- Accuracy: 0.6587
+- Loss: 0.6216
+- 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": 0.621593713760376,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.3988,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2615.29,
+    "eval_steps_per_second": 12.537,
+    "total_flos": 1345426898614272.0,
+    "train_loss": 0.5756891848994237,
+    "train_runtime": 42.7732,
+    "train_samples": 8551,
+    "train_samples_per_second": 9995.753,
+    "train_steps_per_second": 39.745
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.6912751793861389,
+    "eval_loss": 0.621593713760376,
+    "eval_matthews_correlation": 0.0,
+    "eval_runtime": 0.3988,
+    "eval_samples": 1043,
+    "eval_samples_per_second": 2615.29,
+    "eval_steps_per_second": 12.537
+}

logs/events.out.tfevents.1744812195.s_004_m

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf7d19db5c9f1cc513d69b4006f4ad069749da343243d41f4b01ef77e9c4a33
+size 40

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 1345426898614272.0,
+    "train_loss": 0.5756891848994237,
+    "train_runtime": 42.7732,
+    "train_samples": 8551,
+    "train_samples_per_second": 9995.753,
+    "train_steps_per_second": 39.745
+}

trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_metric": 0.621593713760376,
+  "best_model_checkpoint": "tiny_bert_km_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": 0.7628885507583618,
+      "learning_rate": 4.9e-05,
+      "loss": 0.6224,
+      "step": 34
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.621593713760376,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4018,
+      "eval_samples_per_second": 2595.926,
+      "eval_steps_per_second": 12.445,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0041512250900269,
+      "learning_rate": 4.8e-05,
+      "loss": 0.6083,
+      "step": 68
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6220319271087646,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4197,
+      "eval_samples_per_second": 2485.372,
+      "eval_steps_per_second": 11.915,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9402241110801697,
+      "learning_rate": 4.7e-05,
+      "loss": 0.5982,
+      "step": 102
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6912751793861389,
+      "eval_loss": 0.6228198409080505,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.4066,
+      "eval_samples_per_second": 2564.868,
+      "eval_steps_per_second": 12.296,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9954250454902649,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.5783,
+      "step": 136
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6883988380432129,
+      "eval_loss": 0.6298257112503052,
+      "eval_matthews_correlation": 0.08585482785878726,
+      "eval_runtime": 0.4156,
+      "eval_samples_per_second": 2509.564,
+      "eval_steps_per_second": 12.031,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.6896628141403198,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5458,
+      "step": 170
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6788111329078674,
+      "eval_loss": 0.6444757580757141,
+      "eval_matthews_correlation": 0.058343519603323714,
+      "eval_runtime": 0.4047,
+      "eval_samples_per_second": 2576.964,
+      "eval_steps_per_second": 12.354,
+      "step": 170
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.9982967376708984,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.501,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6586769223213196,
+      "eval_loss": 0.669975221157074,
+      "eval_matthews_correlation": 0.11363806297455119,
+      "eval_runtime": 0.413,
+      "eval_samples_per_second": 2525.728,
+      "eval_steps_per_second": 12.108,
+      "step": 204
+    },
+    {
+      "epoch": 6.0,
+      "step": 204,
+      "total_flos": 1345426898614272.0,
+      "train_loss": 0.5756891848994237,
+      "train_runtime": 42.7732,
+      "train_samples_per_second": 9995.753,
+      "train_steps_per_second": 39.745
+    }
+  ],
+  "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
+}