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_qqp
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QQP
+      type: glue
+      args: qqp
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8110066782092505
+    - name: F1
+      type: f1
+      value: 0.7419714314659103
 ---
 
 <!-- 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_qqp
 
-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 QQP dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5052
-- Accuracy: 0.8201
-- F1: 0.7678
-- Combined Score: 0.7939
+- Loss: 0.4153
+- Accuracy: 0.8110
+- F1: 0.7420
+- Combined Score: 0.7765
 
 ## Model description
 

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8110066782092505,
+    "eval_combined_score": 0.7764890548375805,
+    "eval_f1": 0.7419714314659103,
+    "eval_loss": 0.4153307378292084,
+    "eval_runtime": 14.2083,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 2845.51,
+    "eval_steps_per_second": 11.12,
+    "total_flos": 7.633075201391002e+16,
+    "train_loss": 0.3091887569293359,
+    "train_runtime": 2020.2759,
+    "train_samples": 363846,
+    "train_samples_per_second": 9004.859,
+    "train_steps_per_second": 35.193
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.8110066782092505,
+    "eval_combined_score": 0.7764890548375805,
+    "eval_f1": 0.7419714314659103,
+    "eval_loss": 0.4153307378292084,
+    "eval_runtime": 14.2083,
+    "eval_samples": 40430,
+    "eval_samples_per_second": 2845.51,
+    "eval_steps_per_second": 11.12
+}

logs/events.out.tfevents.1744832810.s_004_m

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa7fe003e8990e55b9af3160e6633c730d85a3fa27edfb4c329a67601c9916c
+size 40

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.0,
+    "total_flos": 7.633075201391002e+16,
+    "train_loss": 0.3091887569293359,
+    "train_runtime": 2020.2759,
+    "train_samples": 363846,
+    "train_samples_per_second": 9004.859,
+    "train_steps_per_second": 35.193
+}

trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": 0.4153307378292084,
+  "best_model_checkpoint": "tiny_bert_rand_100_v1_qqp/checkpoint-4266",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 11376,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7541351318359375,
+      "learning_rate": 4.9e-05,
+      "loss": 0.496,
+      "step": 1422
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7838486272569873,
+      "eval_combined_score": 0.7322145289141401,
+      "eval_f1": 0.6805804305712928,
+      "eval_loss": 0.4491816461086273,
+      "eval_runtime": 14.8017,
+      "eval_samples_per_second": 2731.443,
+      "eval_steps_per_second": 10.674,
+      "step": 1422
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.7397406101226807,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4089,
+      "step": 2844
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8033638387336136,
+      "eval_combined_score": 0.7612324811645597,
+      "eval_f1": 0.7191011235955056,
+      "eval_loss": 0.4195970892906189,
+      "eval_runtime": 14.1267,
+      "eval_samples_per_second": 2861.947,
+      "eval_steps_per_second": 11.184,
+      "step": 2844
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.006162405014038,
+      "learning_rate": 4.7e-05,
+      "loss": 0.3518,
+      "step": 4266
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8110066782092505,
+      "eval_combined_score": 0.7764890548375805,
+      "eval_f1": 0.7419714314659103,
+      "eval_loss": 0.4153307378292084,
+      "eval_runtime": 14.1896,
+      "eval_samples_per_second": 2849.272,
+      "eval_steps_per_second": 11.135,
+      "step": 4266
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.5791120529174805,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3062,
+      "step": 5688
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8186495176848875,
+      "eval_combined_score": 0.780485228372211,
+      "eval_f1": 0.7423209390595347,
+      "eval_loss": 0.4295639395713806,
+      "eval_runtime": 14.2354,
+      "eval_samples_per_second": 2840.098,
+      "eval_steps_per_second": 11.099,
+      "step": 5688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.346965789794922,
+      "learning_rate": 4.5e-05,
+      "loss": 0.2689,
+      "step": 7110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8198367548849864,
+      "eval_combined_score": 0.7865778193281611,
+      "eval_f1": 0.7533188837713357,
+      "eval_loss": 0.4466039538383484,
+      "eval_runtime": 13.8417,
+      "eval_samples_per_second": 2920.893,
+      "eval_steps_per_second": 11.415,
+      "step": 7110
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.1513712406158447,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.239,
+      "step": 8532
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8201582982933465,
+      "eval_combined_score": 0.7912292357791229,
+      "eval_f1": 0.7623001732648992,
+      "eval_loss": 0.4361380636692047,
+      "eval_runtime": 13.8654,
+      "eval_samples_per_second": 2915.885,
+      "eval_steps_per_second": 11.395,
+      "step": 8532
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.002156734466553,
+      "learning_rate": 4.3e-05,
+      "loss": 0.2131,
+      "step": 9954
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8231016571852585,
+      "eval_combined_score": 0.7940583854332128,
+      "eval_f1": 0.765015113681167,
+      "eval_loss": 0.46639078855514526,
+      "eval_runtime": 13.9853,
+      "eval_samples_per_second": 2890.887,
+      "eval_steps_per_second": 11.298,
+      "step": 9954
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.098388910293579,
+      "learning_rate": 4.2e-05,
+      "loss": 0.1896,
+      "step": 11376
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8200840959683403,
+      "eval_combined_score": 0.7939181654809773,
+      "eval_f1": 0.7677522349936143,
+      "eval_loss": 0.5052474141120911,
+      "eval_runtime": 13.808,
+      "eval_samples_per_second": 2928.009,
+      "eval_steps_per_second": 11.443,
+      "step": 11376
+    },
+    {
+      "epoch": 8.0,
+      "step": 11376,
+      "total_flos": 7.633075201391002e+16,
+      "train_loss": 0.3091887569293359,
+      "train_runtime": 2020.2759,
+      "train_samples_per_second": 9004.859,
+      "train_steps_per_second": 35.193
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 71100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 7.633075201391002e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}