End of training

README.md

@@ -1,12 +1,27 @@
 ---
+language:
+- en
 base_model: Hartunka/tiny_bert_rand_50_v1
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: tiny_bert_rand_50_v1_sst2
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE SST2
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8027522935779816
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tiny_bert_rand_50_v1_sst2
 
-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 SST2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7671
-- Accuracy: 0.7993
+- Loss: 0.4549
+- Accuracy: 0.8028
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8027522935779816,
+    "eval_loss": 0.45489147305488586,
+    "eval_runtime": 0.3467,
+    "eval_samples": 872,
+    "eval_samples_per_second": 2515.209,
+    "eval_steps_per_second": 11.538,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.20807489963492962,
+    "train_runtime": 273.0937,
+    "train_samples": 67349,
+    "train_samples_per_second": 12330.75,
+    "train_steps_per_second": 48.335
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.8027522935779816,
+    "eval_loss": 0.45489147305488586,
+    "eval_runtime": 0.3467,
+    "eval_samples": 872,
+    "eval_samples_per_second": 2515.209,
+    "eval_steps_per_second": 11.538
+}

logs/events.out.tfevents.1744827247.s_004_m

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22161b006efc0e30ff954a578440acac7ccb90f2fa3ab55df3b2de485b7a5953
+size 40

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 1.0596790573590528e+16,
+    "train_loss": 0.20807489963492962,
+    "train_runtime": 273.0937,
+    "train_samples": 67349,
+    "train_samples_per_second": 12330.75,
+    "train_steps_per_second": 48.335
+}

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.45489147305488586,
+  "best_model_checkpoint": "tiny_bert_rand_50_v1_sst2/checkpoint-264",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1584,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.053354263305664,
+      "learning_rate": 4.9e-05,
+      "loss": 0.4234,
+      "step": 264
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8027522935779816,
+      "eval_loss": 0.45489147305488586,
+      "eval_runtime": 0.3253,
+      "eval_samples_per_second": 2680.347,
+      "eval_steps_per_second": 12.295,
+      "step": 264
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.1799139976501465,
+      "learning_rate": 4.8e-05,
+      "loss": 0.2388,
+      "step": 528
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7935779816513762,
+      "eval_loss": 0.508144736289978,
+      "eval_runtime": 0.3172,
+      "eval_samples_per_second": 2749.385,
+      "eval_steps_per_second": 12.612,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.6632261276245117,
+      "learning_rate": 4.7e-05,
+      "loss": 0.1892,
+      "step": 792
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8038990825688074,
+      "eval_loss": 0.5134162306785583,
+      "eval_runtime": 0.3358,
+      "eval_samples_per_second": 2596.967,
+      "eval_steps_per_second": 11.913,
+      "step": 792
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.277470111846924,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.1562,
+      "step": 1056
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 0.5727466344833374,
+      "eval_runtime": 0.3226,
+      "eval_samples_per_second": 2702.685,
+      "eval_steps_per_second": 12.398,
+      "step": 1056
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.613324165344238,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1309,
+      "step": 1320
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7924311926605505,
+      "eval_loss": 0.6912547945976257,
+      "eval_runtime": 0.324,
+      "eval_samples_per_second": 2691.139,
+      "eval_steps_per_second": 12.345,
+      "step": 1320
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.086341381072998,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.1098,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.7671384215354919,
+      "eval_runtime": 0.3287,
+      "eval_samples_per_second": 2652.474,
+      "eval_steps_per_second": 12.167,
+      "step": 1584
+    },
+    {
+      "epoch": 6.0,
+      "step": 1584,
+      "total_flos": 1.0596790573590528e+16,
+      "train_loss": 0.20807489963492962,
+      "train_runtime": 273.0937,
+      "train_samples_per_second": 12330.75,
+      "train_steps_per_second": 48.335
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 13200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 1.0596790573590528e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}