Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- epoch2/error.log +3 -0
- epoch2/logs.txt +500 -0
- epoch2/model/1_Pooling/config.json +10 -0
- epoch2/model/README.md +773 -0
- epoch2/model/config.json +28 -0
- epoch2/model/config_sentence_transformers.json +14 -0
- epoch2/model/model.safetensors +3 -0
- epoch2/model/modules.json +14 -0
- epoch2/model/sentence_bert_config.json +4 -0
- epoch2/model/tokenizer.json +0 -0
- epoch2/model/tokenizer_config.json +21 -0
- epoch2/output.log +228 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
epoch2/error.log filter=lfs diff=lfs merge=lfs -text
|
epoch2/error.log
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e13044c2943acf7de381650f9b9e82eda0a8d8450ec29408f75290a3cdfe487
|
| 3 |
+
size 17162506
|
epoch2/logs.txt
ADDED
|
@@ -0,0 +1,500 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-02-24 17:30:09 - Load pretrained SentenceTransformer: bert-base-arabertv02
|
| 2 |
+
2026-02-24 17:30:19 - '[Errno -2] Name or service not known' thrown while requesting HEAD https://huggingface.co/bert-base-arabertv02/resolve/main/./modules.json
|
| 3 |
+
2026-02-24 17:30:19 - Retrying in 1s [Retry 1/5].
|
| 4 |
+
2026-02-24 17:30:20 - No sentence-transformers model found with name bert-base-arabertv02. Creating a new one with mean pooling.
|
| 5 |
+
Model is running on: cuda
|
| 6 |
+
2026-02-24 17:30:25 - Reading the training and eval dataset
|
| 7 |
+
2026-02-24 17:31:43 - DatasetDict({
|
| 8 |
+
train: Dataset({
|
| 9 |
+
features: ['anchor', 'positive', 'negative'],
|
| 10 |
+
num_rows: 3954179
|
| 11 |
+
})
|
| 12 |
+
})
|
| 13 |
+
2026-02-24 17:31:43 - DatasetDict({
|
| 14 |
+
train: Dataset({
|
| 15 |
+
features: ['anchor', 'positive', 'negative'],
|
| 16 |
+
num_rows: 1129759
|
| 17 |
+
})
|
| 18 |
+
})
|
| 19 |
+
2026-02-24 17:31:43 - DatasetDict({
|
| 20 |
+
train: Dataset({
|
| 21 |
+
features: ['anchor', 'positive', 'negative'],
|
| 22 |
+
num_rows: 564877
|
| 23 |
+
})
|
| 24 |
+
})
|
| 25 |
+
2026-02-24 17:31:43 - TripletEvaluator: Evaluating the model on the dev-768 dataset (truncated to 768):
|
| 26 |
+
2026-02-24 17:55:01 - Accuracy Cosine Similarity: 79.01%
|
| 27 |
+
2026-02-24 17:55:01 - TripletEvaluator: Evaluating the model on the dev-512 dataset (truncated to 512):
|
| 28 |
+
2026-02-24 18:17:34 - Accuracy Cosine Similarity: 77.91%
|
| 29 |
+
2026-02-24 18:17:34 - TripletEvaluator: Evaluating the model on the dev-256 dataset (truncated to 256):
|
| 30 |
+
2026-02-24 18:39:41 - Accuracy Cosine Similarity: 79.57%
|
| 31 |
+
2026-02-24 18:39:41 - TripletEvaluator: Evaluating the model on the dev-128 dataset (truncated to 128):
|
| 32 |
+
2026-02-24 19:02:02 - Accuracy Cosine Similarity: 78.63%
|
| 33 |
+
2026-02-24 19:02:02 - TripletEvaluator: Evaluating the model on the dev-64 dataset (truncated to 64):
|
| 34 |
+
2026-02-24 19:24:20 - Accuracy Cosine Similarity: 76.00%
|
| 35 |
+
{'loss': '13.01', 'grad_norm': '27.4', 'learning_rate': '6.441e-07', 'epoch': '0.006474'}
|
| 36 |
+
{'loss': '6.428', 'grad_norm': '19.47', 'learning_rate': '1.291e-06', 'epoch': '0.01295'}
|
| 37 |
+
{'loss': '4.365', 'grad_norm': '17.72', 'learning_rate': '1.939e-06', 'epoch': '0.01942'}
|
| 38 |
+
{'loss': '3.585', 'grad_norm': '14.64', 'learning_rate': '2.586e-06', 'epoch': '0.0259'}
|
| 39 |
+
{'loss': '3.183', 'grad_norm': '13.4', 'learning_rate': '3.234e-06', 'epoch': '0.03237'}
|
| 40 |
+
{'loss': '2.873', 'grad_norm': '10.47', 'learning_rate': '3.881e-06', 'epoch': '0.03884'}
|
| 41 |
+
{'loss': '2.634', 'grad_norm': '12.2', 'learning_rate': '4.528e-06', 'epoch': '0.04532'}
|
| 42 |
+
{'loss': '2.605', 'grad_norm': '12.74', 'learning_rate': '5.176e-06', 'epoch': '0.05179'}
|
| 43 |
+
{'loss': '2.31', 'grad_norm': '12.29', 'learning_rate': '5.823e-06', 'epoch': '0.05827'}
|
| 44 |
+
{'loss': '2.236', 'grad_norm': '10.22', 'learning_rate': '6.47e-06', 'epoch': '0.06474'}
|
| 45 |
+
{'loss': '2.155', 'grad_norm': '9.492', 'learning_rate': '7.118e-06', 'epoch': '0.07121'}
|
| 46 |
+
{'loss': '2.019', 'grad_norm': '9.747', 'learning_rate': '7.765e-06', 'epoch': '0.07769'}
|
| 47 |
+
{'loss': '1.926', 'grad_norm': '9.491', 'learning_rate': '8.412e-06', 'epoch': '0.08416'}
|
| 48 |
+
{'loss': '1.927', 'grad_norm': '8.972', 'learning_rate': '9.06e-06', 'epoch': '0.09064'}
|
| 49 |
+
{'loss': '1.866', 'grad_norm': '10.02', 'learning_rate': '9.707e-06', 'epoch': '0.09711'}
|
| 50 |
+
{'loss': '1.796', 'grad_norm': '9.32', 'learning_rate': '1.035e-05', 'epoch': '0.1036'}
|
| 51 |
+
{'loss': '1.731', 'grad_norm': '8.47', 'learning_rate': '1.1e-05', 'epoch': '0.1101'}
|
| 52 |
+
{'loss': '1.725', 'grad_norm': '7.867', 'learning_rate': '1.165e-05', 'epoch': '0.1165'}
|
| 53 |
+
{'loss': '1.619', 'grad_norm': '9.521', 'learning_rate': '1.23e-05', 'epoch': '0.123'}
|
| 54 |
+
{'loss': '1.634', 'grad_norm': '9.193', 'learning_rate': '1.294e-05', 'epoch': '0.1295'}
|
| 55 |
+
{'loss': '1.604', 'grad_norm': '9.547', 'learning_rate': '1.359e-05', 'epoch': '0.136'}
|
| 56 |
+
{'loss': '1.548', 'grad_norm': '8.025', 'learning_rate': '1.424e-05', 'epoch': '0.1424'}
|
| 57 |
+
{'loss': '1.542', 'grad_norm': '8.197', 'learning_rate': '1.489e-05', 'epoch': '0.1489'}
|
| 58 |
+
{'loss': '1.507', 'grad_norm': '7.923', 'learning_rate': '1.553e-05', 'epoch': '0.1554'}
|
| 59 |
+
{'loss': '1.48', 'grad_norm': '7.746', 'learning_rate': '1.618e-05', 'epoch': '0.1619'}
|
| 60 |
+
{'loss': '1.462', 'grad_norm': '10.12', 'learning_rate': '1.683e-05', 'epoch': '0.1683'}
|
| 61 |
+
{'loss': '1.446', 'grad_norm': '7.806', 'learning_rate': '1.748e-05', 'epoch': '0.1748'}
|
| 62 |
+
{'loss': '1.424', 'grad_norm': '6.649', 'learning_rate': '1.812e-05', 'epoch': '0.1813'}
|
| 63 |
+
{'loss': '1.393', 'grad_norm': '7.031', 'learning_rate': '1.877e-05', 'epoch': '0.1877'}
|
| 64 |
+
{'loss': '1.352', 'grad_norm': '6.146', 'learning_rate': '1.942e-05', 'epoch': '0.1942'}
|
| 65 |
+
2026-02-24 20:40:33 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 0.19422189851905802 after 6000 steps (truncated to 768):
|
| 66 |
+
2026-02-24 21:08:51 - Accuracy Cosine Similarity: 95.64%
|
| 67 |
+
2026-02-24 21:08:51 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 0.19422189851905802 after 6000 steps (truncated to 512):
|
| 68 |
+
2026-02-24 21:36:55 - Accuracy Cosine Similarity: 95.66%
|
| 69 |
+
2026-02-24 21:36:55 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 0.19422189851905802 after 6000 steps (truncated to 256):
|
| 70 |
+
2026-02-24 22:05:02 - Accuracy Cosine Similarity: 95.60%
|
| 71 |
+
2026-02-24 22:05:02 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 0.19422189851905802 after 6000 steps (truncated to 128):
|
| 72 |
+
2026-02-24 22:33:12 - Accuracy Cosine Similarity: 95.46%
|
| 73 |
+
2026-02-24 22:33:12 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 0.19422189851905802 after 6000 steps (truncated to 64):
|
| 74 |
+
2026-02-24 23:01:40 - Accuracy Cosine Similarity: 95.13%
|
| 75 |
+
{'eval_train_loss': '1.216', 'eval_dev-768_cosine_accuracy': '0.9564', 'eval_dev-512_cosine_accuracy': '0.9566', 'eval_dev-256_cosine_accuracy': '0.956', 'eval_dev-128_cosine_accuracy': '0.9546', 'eval_dev-64_cosine_accuracy': '0.9513', 'eval_sequential_score': '0.9564', 'eval_train_runtime': '9876', 'eval_train_samples_per_second': '114.4', 'eval_train_steps_per_second': '1.787', 'epoch': '0.1942'}
|
| 76 |
+
2026-02-24 23:01:40 - Saving model checkpoint to output/arabert_20260224_1730/checkpoint-6000
|
| 77 |
+
2026-02-24 23:01:40 - Save model to output/arabert_20260224_1730/checkpoint-6000
|
| 78 |
+
{'loss': '1.372', 'grad_norm': '8.833', 'learning_rate': '1.999e-05', 'epoch': '0.2007'}
|
| 79 |
+
{'loss': '1.37', 'grad_norm': '6.729', 'learning_rate': '1.992e-05', 'epoch': '0.2072'}
|
| 80 |
+
{'loss': '1.352', 'grad_norm': '6.586', 'learning_rate': '1.985e-05', 'epoch': '0.2136'}
|
| 81 |
+
{'loss': '1.288', 'grad_norm': '6.568', 'learning_rate': '1.978e-05', 'epoch': '0.2201'}
|
| 82 |
+
{'loss': '1.271', 'grad_norm': '6.606', 'learning_rate': '1.971e-05', 'epoch': '0.2266'}
|
| 83 |
+
{'loss': '1.243', 'grad_norm': '7.913', 'learning_rate': '1.963e-05', 'epoch': '0.2331'}
|
| 84 |
+
{'loss': '1.23', 'grad_norm': '6.931', 'learning_rate': '1.956e-05', 'epoch': '0.2395'}
|
| 85 |
+
{'loss': '1.212', 'grad_norm': '6.979', 'learning_rate': '1.949e-05', 'epoch': '0.246'}
|
| 86 |
+
{'loss':{'loss': '1.37', 'grad_norm': '6.732', 'learning_rate': '1.992e-05', 'epoch': '0.2072'}
|
| 87 |
+
{'loss': '1.352', 'grad_norm': '6.583', 'learning_rate': '1.985e-05'{'loss': '1.288', 'grad_norm': '6.564', 'learning_rate': '1.978e-05', 'epoch': '0.2201'}
|
| 88 |
+
':{'loss': '1.271', 'grad_norm': '6.606', 'learning_rate': '1.971e-05', 'epoch': '0.2266'}
|
| 89 |
+
{'loss': '1.243', 'grad_norm': '7.906', 'learning_rate': '1.963e-05', 'epoch': '0.2331'}
|
| 90 |
+
{'loss': '1.23', 'grad_norm': '6.921', 'learning_rate': '1.956e-05', 'epoch': '0.2395'}
|
| 91 |
+
{'loss': '1.212', 'grad_norm': '6.985', 'learning_rate': '1.949e-05', 'epoch': '0.246'}
|
| 92 |
+
{'loss': '1.222', 'grad_norm': '7.511', 'learning_rate': '1.942e-05', 'epoch': '0.2525'}
|
| 93 |
+
{'loss': '1.212', 'grad_norm': '7.834', 'learning_rate': '1.935e-05', 'epoch': '0.259'}
|
| 94 |
+
{'loss': '1.199', 'grad_norm': '5.273', 'learning_rate': '1.927e-05', 'epoch': '0.2654'}
|
| 95 |
+
{'loss': '1.207', 'grad_norm': '7.454', 'learning_rate': '1.92e-05', 'epoch': '0.2719'}
|
| 96 |
+
{'loss': '1.197', 'grad_norm': '7.585', 'learning_rate': '1.913e-05', 'epoch': '0.2784'}
|
| 97 |
+
{'loss': '1.128', 'grad_norm': '7.16', 'learning_rate': '1.906e-05', 'epoch': '0.2849'}
|
| 98 |
+
{'loss': '1.139', 'grad_norm': '6.354', 'learning_rate': '1.899e-05', 'epoch': '0.2913'}
|
| 99 |
+
{'loss': '1.197', 'grad_norm': '8.433', 'learning_rate': '1.891e-05', 'epoch': '0.2978'}
|
| 100 |
+
{'loss': '1.099', 'grad_norm': '5.537', 'learning_rate': '1.884e-05', 'epoch': '0.3043'}
|
| 101 |
+
{'loss': '1.133', 'grad_norm': '7.014', 'learning_rate': '1.877e-05', 'epoch': '0.3108'}
|
| 102 |
+
{'loss': '1.104', 'grad_norm': '7.172', 'learning_rate': '1.87e-05', 'epoch': '0.3172'}
|
| 103 |
+
{'loss': '1.116', 'grad_norm': '7.246', 'learning_rate': '1.863e-05', 'epoch': '0.3237'}
|
| 104 |
+
{'loss': '1.083', 'grad_norm': '7.252', 'learning_rate': '1.855e-05', 'epoch': '0.3302'}
|
| 105 |
+
{'loss': '1.043', 'grad_norm': '9.376', 'learning_rate': '1.848e-05', 'epoch': '0.3367'}
|
| 106 |
+
{'loss': '1.104', 'grad_norm': '6.334', 'learning_rate': '1.841e-05', 'epoch': '0.3431'}
|
| 107 |
+
{'loss': '1.074', 'grad_norm': '8.013', 'learning_rate': '1.834e-05', 'epoch': '0.3496'}
|
| 108 |
+
{'loss': '1.075', 'grad_norm': '6.887', 'learning_rate': '1.827e-05', 'epoch': '0.3561'}
|
| 109 |
+
{'loss': '1.059', 'grad_norm': '6.77', 'learning_rate': '1.819e-05', 'epoch': '0.3625'}
|
| 110 |
+
{'loss': '1.063', 'grad_norm': '5.884', 'learning_rate': '1.812e-05', 'epoch': '0.369'}
|
| 111 |
+
{'loss': '1.025', 'grad_norm': '4.584', 'learning_rate': '1.805e-05', 'epoch': '0.3755'}
|
| 112 |
+
{'loss': '1.049', 'grad_norm': '5.729', 'learning_rate': '1.798e-05', 'epoch': '0.382'}
|
| 113 |
+
{'loss': '1.045', 'grad_norm': '4.304', 'learning_rate': '1.791e-05', 'epoch': '0.3884'}
|
| 114 |
+
2026-02-25 16:31:58 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 0.38844379703811605 after 12000 steps (truncated to 768):
|
| 115 |
+
2026-02-25 16:53:08 - Accuracy Cosine Similarity: 96.68%
|
| 116 |
+
2026-02-25 16:53:08 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 0.38844379703811605 after 12000 steps (truncated to 512):
|
| 117 |
+
2026-02-25 17:13:37 - Accuracy Cosine Similarity: 96.67%
|
| 118 |
+
2026-02-25 17:13:37 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 0.38844379703811605 after 12000 steps (truncated to 256):
|
| 119 |
+
2026-02-25 17:34:09 - Accuracy Cosine Similarity: 96.64%
|
| 120 |
+
2026-02-25 17:34:09 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 0.38844379703811605 after 12000 steps (truncated to 128):
|
| 121 |
+
2026-02-25 17:54:44 - Accuracy Cosine Similarity: 96.56%
|
| 122 |
+
2026-02-25 17:54:44 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 0.38844379703811605 after 12000 steps (truncated to 64):
|
| 123 |
+
2026-02-25 18:15:17 - Accuracy Cosine Similarity: 96.28%
|
| 124 |
+
{'eval_train_loss': '0.5325', 'eval_dev-768_cosine_accuracy': '0.9668', 'eval_dev-512_cosine_accuracy': '0.9667', 'eval_dev-256_cosine_accuracy': '0.9664', 'eval_dev-128_cosine_accuracy': '0.9656', 'eval_dev-64_cosine_accuracy': '0.9628', 'eval_sequential_score': '0.9668', 'eval_train_runtime': '9281', 'eval_train_samples_per_second': '121.7', 'eval_train_steps_per_second': '15.22', 'epoch': '0.3884'}
|
| 125 |
+
2026-02-25 18:15:17 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-12000
|
| 126 |
+
2026-02-25 18:15:17 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-12000
|
| 127 |
+
{'loss': '0.9883', 'grad_norm': '5.449', 'learning_rate': '1.783e-05', 'epoch': '0.3949'}
|
| 128 |
+
{'loss': '0.9907', 'grad_norm': '5.808', 'learning_rate': '1.776e-05', 'epoch': '0.4014'}
|
| 129 |
+
{'loss': '1.022', 'grad_norm': '6.168', 'learning_rate': '1.769e-05', 'epoch': '0.4079'}
|
| 130 |
+
{'loss': '0.987', 'grad_norm': '5.675', 'learning_rate': '1.762e-05', 'epoch': '0.4143'}
|
| 131 |
+
{'loss': '1.033', 'grad_norm': '5.961', 'learning_rate': '1.755e-05', 'epoch': '0.4208'}
|
| 132 |
+
{'loss': '0.9989', 'grad_norm': '7.682', 'learning_rate': '1.748e-05', 'epoch': '0.4273'}
|
| 133 |
+
{'loss': '0.9805', 'grad_norm': '6.046', 'learning_rate': '1.74e-05', 'epoch': '0.4338'}
|
| 134 |
+
{'loss': '0.9484', 'grad_norm': '6.129', 'learning_rate': '1.733e-05', 'epoch': '0.4402'}
|
| 135 |
+
{'loss': '0.9937', 'grad_norm': '4.2', 'learning_rate': '1.726e-05', 'epoch': '0.4467'}
|
| 136 |
+
{'loss': '1.016', 'grad_norm': '7.164', 'learning_rate': '1.719e-05', 'epoch': '0.4532'}
|
| 137 |
+
{'loss': '0.9726', 'grad_norm': '5.905', 'learning_rate': '1.712e-05', 'epoch': '0.4597'}
|
| 138 |
+
{'loss': '0.96', 'grad_norm': '5.824', 'learning_rate': '1.704e-05', 'epoch': '0.4661'}
|
| 139 |
+
{'loss': '0.9528', 'grad_norm': '6.058', 'learning_rate': '1.697e-05', 'epoch': '0.4726'}
|
| 140 |
+
{'loss': '0.9292', 'grad_norm': '4.911', 'learning_rate': '1.69e-05', 'epoch': '0.4791'}
|
| 141 |
+
{'loss': '0.9157', 'grad_norm': '6.308', 'learning_rate': '1.683e-05', 'epoch': '0.4856'}
|
| 142 |
+
{'loss': '0.9244', 'grad_norm': '5.036', 'learning_rate': '1.676e-05', 'epoch': '0.492'}
|
| 143 |
+
{'loss': '0.9192', 'grad_norm': '3.666', 'learning_rate': '1.668e-05', 'epoch': '0.4985'}
|
| 144 |
+
{'loss': '0.9424', 'grad_norm': '4.06', 'learning_rate': '1.661e-05', 'epoch': '0.505'}
|
| 145 |
+
{'loss': '0.9067', 'grad_norm': '5.872', 'learning_rate': '1.654e-05', 'epoch': '0.5115'}
|
| 146 |
+
{'loss': '0.9334', 'grad_norm': '5.868', 'learning_rate': '1.647e-05', 'epoch': '0.5179'}
|
| 147 |
+
{'loss': '0.8922', 'grad_norm': '6.681', 'learning_rate': '1.64e-05', 'epoch': '0.5244'}
|
| 148 |
+
{'loss': '0.9122', 'grad_norm': '7.907', 'learning_rate': '1.632e-05', 'epoch': '0.5309'}
|
| 149 |
+
{'loss': '0.8825', 'grad_norm': '6.144', 'learning_rate': '1.625e-05', 'epoch': '0.5373'}
|
| 150 |
+
{'loss': '0.9069', 'grad_norm': '6.138', 'learning_rate': '1.618e-05', 'epoch': '0.5438'}
|
| 151 |
+
{'loss': '0.894', 'grad_norm': '6.968', 'learning_rate': '1.611e-05', 'epoch': '0.5503'}
|
| 152 |
+
{'loss': '0.8898', 'grad_norm': '6.487', 'learning_rate': '1.604e-05', 'epoch': '0.5568'}
|
| 153 |
+
{'loss': '0.8735', 'grad_norm': '4.058', 'learning_rate': '1.596e-05', 'epoch': '0.5632'}
|
| 154 |
+
{'loss': '0.8694', 'grad_norm': '5.403', 'learning_rate': '1.589e-05', 'epoch': '0.5697'}
|
| 155 |
+
{'loss': '0.8776', 'grad_norm': '6.723', 'learning_rate': '1.582e-05', 'epoch': '0.5762'}
|
| 156 |
+
{'loss': '0.8664', 'grad_norm': '4.427', 'learning_rate': '1.575e-05', 'epoch': '0.5827'}
|
| 157 |
+
2026-02-25 20:05:35 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 0.5826656955571741 after 18000 steps (truncated to 768):
|
| 158 |
+
2026-02-25 20:26:21 - Accuracy Cosine Similarity: 97.12%
|
| 159 |
+
2026-02-25 20:26:21 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 0.5826656955571741 after 18000 steps (truncated to 512):
|
| 160 |
+
2026-02-25 20:46:59 - Accuracy Cosine Similarity: 97.11%
|
| 161 |
+
2026-02-25 20:46:59 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 0.5826656955571741 after 18000 steps (truncated to 256):
|
| 162 |
+
2026-02-25 21:07:40 - Accuracy Cosine Similarity: 97.09%
|
| 163 |
+
2026-02-25 21:07:40 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 0.5826656955571741 after 18000 steps (truncated to 128):
|
| 164 |
+
2026-02-25 21:28:20 - Accuracy Cosine Similarity: 97.03%
|
| 165 |
+
2026-02-25 21:28:20 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 0.5826656955571741 after 18000 steps (truncated to 64):
|
| 166 |
+
2026-02-25 21:49:02 - Accuracy Cosine Similarity: 96.82%
|
| 167 |
+
{'eval_train_loss': '0.4541', 'eval_dev-768_cosine_accuracy': '0.9712', 'eval_dev-512_cosine_accuracy': '0.9711', 'eval_dev-256_cosine_accuracy': '0.9709', 'eval_dev-128_cosine_accuracy': '0.9703', 'eval_dev-64_cosine_accuracy': '0.9682', 'eval_sequential_score': '0.9712', 'eval_train_runtime': '9294', 'eval_train_samples_per_second': '121.6', 'eval_train_steps_per_second': '15.19', 'epoch': '0.5827'}
|
| 168 |
+
2026-02-25 21:49:02 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-18000
|
| 169 |
+
2026-02-25 21:49:02 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-18000
|
| 170 |
+
|
| 171 |
+
2026-02-26 14:22:01 - Load pretrained SentenceTransformer: bert-base-arabertv02
|
| 172 |
+
2026-02-26 14:22:14 - '[Errno -2] Name or service not known' thrown while requesting HEAD https://huggingface.co/bert-base-arabertv02/resolve/main/./modules.json
|
| 173 |
+
2026-02-26 14:22:14 - Retrying in 1s [Retry 1/5].
|
| 174 |
+
2026-02-26 14:22:15 - No sentence-transformers model found with name bert-base-arabertv02. Creating a new one with mean pooling.
|
| 175 |
+
2026-02-26 14:23:53 - Use pytorch device_name: cuda:0
|
| 176 |
+
2026-02-26 14:23:53 - Load pretrained SentenceTransformer: /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-18000
|
| 177 |
+
{'loss': '0.8727', 'grad_norm': '5.438', 'learning_rate': '1.568e-05', 'epoch': '0.5891'}
|
| 178 |
+
{'loss': '0.8524', 'grad_norm': '5.458', 'learning_rate': '1.56e-05', 'epoch': '0.5956'}
|
| 179 |
+
{'loss': '0.8995', 'grad_norm': '6.666', 'learning_rate': '1.553e-05', 'epoch': '0.6021'}
|
| 180 |
+
{'loss': '0.836', 'grad_norm': '5.681', 'learning_rate': '1.546e-05', 'epoch': '0.6086'}
|
| 181 |
+
{'loss': '0.8628', 'grad_norm': '6.571', 'learning_rate': '1.539e-05', 'epoch': '0.615'}
|
| 182 |
+
{'loss': '0.8244', 'grad_norm': '6.389', 'learning_rate': '1.532e-05', 'epoch': '0.6215'}
|
| 183 |
+
{'loss': '0.8647', 'grad_norm': '4.987', 'learning_rate': '1.525e-05', 'epoch': '0.628'}
|
| 184 |
+
{'loss': '0.8479', 'grad_norm': '4.451', 'learning_rate': '1.517e-05', 'epoch': '0.6345'}
|
| 185 |
+
{'loss': '0.8204', 'grad_norm': '5.356', 'learning_rate': '1.51e-05', 'epoch': '0.6409'}
|
| 186 |
+
{'loss': '0.8359', 'grad_norm': '5.146', 'learning_rate': '1.503e-05', 'epoch': '0.6474'}
|
| 187 |
+
{'loss': '0.7952', 'grad_norm': '4.308', 'learning_rate': '1.496e-05', 'epoch': '0.6539'}
|
| 188 |
+
{'loss': '0.8375', 'grad_norm': '5.216', 'learning_rate': '1.489e-05', 'epoch': '0.6604'}
|
| 189 |
+
{'loss': '0.8364', 'grad_norm': '5.812', 'learning_rate': '1.481e-05', 'epoch': '0.6668'}
|
| 190 |
+
{'loss': '0.8131', 'grad_norm': '5.52', 'learning_rate': '1.474e-05', 'epoch': '0.6733'}
|
| 191 |
+
{'loss': '0.831', 'grad_norm': '6.452', 'learning_rate': '1.467e-05', 'epoch': '0.6798'}
|
| 192 |
+
{'loss': '0.8295', 'grad_norm': '4.274', 'learning_rate': '1.46e-05', 'epoch': '0.6863'}
|
| 193 |
+
{'loss': '0.7865', 'grad_norm': '4.77', 'learning_rate': '1.453e-05', 'epoch': '0.6927'}
|
| 194 |
+
{'loss': '0.796', 'grad_norm': '5.027', 'learning_rate': '1.445e-05', 'epoch': '0.6992'}
|
| 195 |
+
{'loss': '0.8287', 'grad_norm': '4.826', 'learning_rate': '1.438e-05', 'epoch': '0.7057'}
|
| 196 |
+
{'loss': '0.8214', 'grad_norm': '4.381', 'learning_rate': '1.431e-05', 'epoch': '0.7121'}
|
| 197 |
+
{'loss': '0.7879', 'grad_norm': '6.475', 'learning_rate': '1.424e-05', 'epoch': '0.7186'}
|
| 198 |
+
{'loss': '0.8139', 'grad_norm': '5.295', 'learning_rate': '1.417e-05', 'epoch': '0.7251'}
|
| 199 |
+
{'loss': '0.7849', 'grad_norm': '5.051', 'learning_rate': '1.409e-05', 'epoch': '0.7316'}
|
| 200 |
+
{'loss': '0.788', 'grad_norm': '5.113', 'learning_rate': '1.402e-05', 'epoch': '0.738'}
|
| 201 |
+
{'loss': '0.7725', 'grad_norm': '4.049', 'learning_rate': '1.395e-05', 'epoch': '0.7445'}
|
| 202 |
+
{'loss': '0.8086', 'grad_norm': '4.646', 'learning_rate': '1.388e-05', 'epoch': '0.751'}
|
| 203 |
+
{'loss': '0.7687', 'grad_norm': '5.049', 'learning_rate': '1.381e-05', 'epoch': '0.7575'}
|
| 204 |
+
{'loss': '0.7828', 'grad_norm': '6.568', 'learning_rate': '1.373e-05', 'epoch': '0.7639'}
|
| 205 |
+
{'loss': '0.7518', 'grad_norm': '5.9', 'learning_rate': '1.366e-05', 'epoch': '0.7704'}
|
| 206 |
+
{'loss': '0.7599', 'grad_norm': '6.338', 'learning_rate': '1.359e-05', 'epoch': '0.7769'}
|
| 207 |
+
2026-02-26 16:19:09 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 0.7768875940762321 after 24000 steps (truncated to 768):
|
| 208 |
+
2026-02-26 16:40:53 - Accuracy Cosine Similarity: 97.37%
|
| 209 |
+
2026-02-26 16:40:53 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 0.7768875940762321 after 24000 steps (truncated to 512):
|
| 210 |
+
2026-02-26 17:02:09 - Accuracy Cosine Similarity: 97.38%
|
| 211 |
+
2026-02-26 17:02:09 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 0.7768875940762321 after 24000 steps (truncated to 256):
|
| 212 |
+
2026-02-26 17:23:27 - Accuracy Cosine Similarity: 97.38%
|
| 213 |
+
2026-02-26 17:23:27 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 0.7768875940762321 after 24000 steps (truncated to 128):
|
| 214 |
+
2026-02-26 17:44:42 - Accuracy Cosine Similarity: 97.34%
|
| 215 |
+
2026-02-26 17:44:42 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 0.7768875940762321 after 24000 steps (truncated to 64):
|
| 216 |
+
2026-02-26 18:06:06 - Accuracy Cosine Similarity: 97.18%
|
| 217 |
+
{'eval_train_loss': '0.4041', 'eval_dev-768_cosine_accuracy': '0.9737', 'eval_dev-512_cosine_accuracy': '0.9738', 'eval_dev-256_cosine_accuracy': '0.9738', 'eval_dev-128_cosine_accuracy': '0.9734', 'eval_dev-64_cosine_accuracy': '0.9718', 'eval_sequential_score': '0.9737', 'eval_train_runtime': '9673', 'eval_train_samples_per_second': '116.8', 'eval_train_steps_per_second': '14.6', 'epoch': '0.7769'}
|
| 218 |
+
2026-02-26 18:06:06 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-24000
|
| 219 |
+
2026-02-26 18:06:06 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-24000
|
| 220 |
+
{'loss': '0.7332', 'grad_norm': '4.95', 'learning_rate': '1.352e-05', 'epoch': '0.7834'}
|
| 221 |
+
{'loss': '0.7476', 'grad_norm': '4.513', 'learning_rate': '1.345e-05', 'epoch': '0.7898'}
|
| 222 |
+
{'loss': '0.7806', 'grad_norm': '5.095', 'learning_rate': '1.337e-05', 'epoch': '0.7963'}
|
| 223 |
+
{'loss': '0.7511', 'grad_norm': '5.826', 'learning_rate': '1.33e-05', 'epoch': '0.8028'}
|
| 224 |
+
{'loss': '0.7652', 'grad_norm': '6.09', 'learning_rate': '1.323e-05', 'epoch': '0.8093'}
|
| 225 |
+
{'loss': '0.7883', 'grad_norm': '4.332', 'learning_rate': '1.316e-05', 'epoch': '0.8157'}
|
| 226 |
+
{'loss': '0.7305', 'grad_norm': '5.749', 'learning_rate': '1.309e-05', 'epoch': '0.8222'}
|
| 227 |
+
{'loss': '0.7308', 'grad_norm': '4.871', 'learning_rate': '1.302e-05', 'epoch': '0.8287'}
|
| 228 |
+
{'loss': '0.7368', 'grad_norm': '4.618', 'learning_rate': '1.294e-05', 'epoch': '0.8352'}
|
| 229 |
+
{'loss': '0.7432', 'grad_norm': '4.836', 'learning_rate': '1.287e-05', 'epoch': '0.8416'}
|
| 230 |
+
{'loss': '0.7046', 'grad_norm': '4.988', 'learning_rate': '1.28e-05', 'epoch': '0.8481'}
|
| 231 |
+
{'loss': '0.7476', 'grad_norm': '4.596', 'learning_rate': '1.273e-05', 'epoch': '0.8546'}
|
| 232 |
+
{'loss': '0.7212', 'grad_norm': '5.712', 'learning_rate': '1.266e-05', 'epoch': '0.8611'}
|
| 233 |
+
{'loss': '0.7335', 'grad_norm': '3.99', 'learning_rate': '1.258e-05', 'epoch': '0.8675'}
|
| 234 |
+
{'loss': '0.7415', 'grad_norm': '5.446', 'learning_rate': '1.251e-05', 'epoch': '0.874'}
|
| 235 |
+
{'loss': '0.6937', 'grad_norm': '5.257', 'learning_rate': '1.244e-05', 'epoch': '0.8805'}
|
| 236 |
+
{'loss': '0.7294', 'grad_norm': '5.302', 'learning_rate': '1.237e-05', 'epoch': '0.8869'}
|
| 237 |
+
{'loss': '0.7436', 'grad_norm': '3.847', 'learning_rate': '1.23e-05', 'epoch': '0.8934'}
|
| 238 |
+
{'loss': '0.7093', 'grad_norm': '6.182', 'learning_rate': '1.222e-05', 'epoch': '0.8999'}
|
| 239 |
+
{'loss': '0.748', 'grad_norm': '5.445', 'learning_rate': '1.215e-05', 'epoch': '0.9064'}
|
| 240 |
+
{'loss': '0.7039', 'grad_norm': '5.002', 'learning_rate': '1.208e-05', 'epoch': '0.9128'}
|
| 241 |
+
{'loss': '0.7091', 'grad_norm': '5.085', 'learning_rate': '1.201e-05', 'epoch': '0.9193'}
|
| 242 |
+
{'loss': '0.7019', 'grad_norm': '5.379', 'learning_rate': '1.194e-05', 'epoch': '0.9258'}
|
| 243 |
+
{'loss': '0.7081', 'grad_norm': '5.63', 'learning_rate': '1.186e-05', 'epoch': '0.9323'}
|
| 244 |
+
{'loss': '0.6833', 'grad_norm': '2.541', 'learning_rate': '1.179e-05', 'epoch': '0.9387'}
|
| 245 |
+
{'loss': '0.6982', 'grad_norm': '5.714', 'learning_rate': '1.172e-05', 'epoch': '0.9452'}
|
| 246 |
+
{'loss': '0.7249', 'grad_norm': '5.051', 'learning_rate': '1.165e-05', 'epoch': '0.9517'}
|
| 247 |
+
{'loss': '0.7282', 'grad_norm': '6.322', 'learning_rate': '1.158e-05', 'epoch': '0.9582'}
|
| 248 |
+
{'loss': '0.7147', 'grad_norm': '4.961', 'learning_rate': '1.15e-05', 'epoch': '0.9646'}
|
| 249 |
+
{'loss': '0.6742', 'grad_norm': '4.871', 'learning_rate': '1.143e-05', 'epoch': '0.9711'}
|
| 250 |
+
2026-02-26 19:59:22 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 0.9711094925952901 after 30000 steps (truncated to 768):
|
| 251 |
+
2026-02-26 20:20:41 - Accuracy Cosine Similarity: 97.58%
|
| 252 |
+
2026-02-26 20:20:41 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 0.9711094925952901 after 30000 steps (truncated to 512):
|
| 253 |
+
2026-02-26 20:42:02 - Accuracy Cosine Similarity: 97.59%
|
| 254 |
+
2026-02-26 20:42:02 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 0.9711094925952901 after 30000 steps (truncated to 256):
|
| 255 |
+
2026-02-26 21:03:17 - Accuracy Cosine Similarity: 97.61%
|
| 256 |
+
2026-02-26 21:03:17 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 0.9711094925952901 after 30000 steps (truncated to 128):
|
| 257 |
+
2026-02-26 21:24:42 - Accuracy Cosine Similarity: 97.57%
|
| 258 |
+
2026-02-26 21:24:42 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 0.9711094925952901 after 30000 steps (truncated to 64):
|
| 259 |
+
2026-02-26 21:46:03 - Accuracy Cosine Similarity: 97.42%
|
| 260 |
+
{'eval_train_loss': '0.364', 'eval_dev-768_cosine_accuracy': '0.9758', 'eval_dev-512_cosine_accuracy': '0.9759', 'eval_dev-256_cosine_accuracy': '0.9761', 'eval_dev-128_cosine_accuracy': '0.9757', 'eval_dev-64_cosine_accuracy': '0.9742', 'eval_sequential_score': '0.9758', 'eval_train_runtime': '9649', 'eval_train_samples_per_second': '117.1', 'eval_train_steps_per_second': '14.64', 'epoch': '0.9711'}
|
| 261 |
+
2026-02-26 21:46:03 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-30000
|
| 262 |
+
2026-02-26 21:46:03 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-30000
|
| 263 |
+
{'loss': '0.6901', 'grad_norm': '3.348', 'learning_rate': '1.136e-05', 'epoch': '0.9776'}
|
| 264 |
+
{'loss': '0.7067', 'grad_norm': '3.76', 'learning_rate': '1.129e-05', 'epoch': '0.9841'}
|
| 265 |
+
{'loss': '0.7166', 'grad_norm': '4.729', 'learning_rate': '1.122e-05', 'epoch': '0.9905'}
|
| 266 |
+
{'loss': '0.68', 'grad_norm': '4.648', 'learning_rate': '1.114e-05', 'epoch': '0.997'}
|
| 267 |
+
{'loss': '0.6846', 'grad_norm': '4.427', 'learning_rate': '1.107e-05', 'epoch': '1.003'}
|
| 268 |
+
{'loss': '0.6723', 'grad_norm': '4.459', 'learning_rate': '1.1e-05', 'epoch': '1.01'}
|
| 269 |
+
{'loss': '0.6573', 'grad_norm': '6.387', 'learning_rate': '1.093e-05', 'epoch': '1.016'}
|
| 270 |
+
{'loss': '0.6895', 'grad_norm': '4.1', 'learning_rate': '1.086e-05', 'epoch': '1.023'}
|
| 271 |
+
{'loss': '0.6588', 'grad_norm': '5.927', 'learning_rate': '1.079e-05', 'epoch': '1.029'}
|
| 272 |
+
{'loss': '0.6517', 'grad_norm': '5.9', 'learning_rate': '1.071e-05', 'epoch': '1.036'}
|
| 273 |
+
{'loss': '0.6498', 'grad_norm': '4.736', 'learning_rate': '1.064e-05', 'epoch': '1.042'}
|
| 274 |
+
{'loss': '0.6836', 'grad_norm': '5.029', 'learning_rate': '1.057e-05', 'epoch': '1.049'}
|
| 275 |
+
{'loss': '0.6819', 'grad_norm': '2.595', 'learning_rate': '1.05e-05', 'epoch': '1.055'}
|
| 276 |
+
{'loss': '0.6463', 'grad_norm': '4.963', 'learning_rate': '1.043e-05', 'epoch': '1.062'}
|
| 277 |
+
{'loss': '0.6645', 'grad_norm': '5.046', 'learning_rate': '1.035e-05', 'epoch': '1.068'}
|
| 278 |
+
{'loss': '0.6518', 'grad_norm': '3.307', 'learning_rate': '1.028e-05', 'epoch': '1.075'}
|
| 279 |
+
{'loss': '0.6235', 'grad_norm': '3.848', 'learning_rate': '1.021e-05', 'epoch': '1.081'}
|
| 280 |
+
{'loss': '0.6302', 'grad_norm': '4.664', 'learning_rate': '1.014e-05', 'epoch': '1.088'}
|
| 281 |
+
{'loss': '0.6452', 'grad_norm': '5.47', 'learning_rate': '1.007e-05', 'epoch': '1.094'}
|
| 282 |
+
{'loss': '0.6477', 'grad_norm': '5.26', 'learning_rate': '9.994e-06', 'epoch': '1.101'}
|
| 283 |
+
{'loss': '0.6084', 'grad_norm': '4.313', 'learning_rate': '9.922e-06', 'epoch': '1.107'}
|
| 284 |
+
{'loss': '0.6259', 'grad_norm': '6.499', 'learning_rate': '9.85e-06', 'epoch': '1.114'}
|
| 285 |
+
{'loss': '0.607', 'grad_norm': '3.922', 'learning_rate': '9.778e-06', 'epoch': '1.12'}
|
| 286 |
+
{'loss': '0.5977', 'grad_norm': '5.37', 'learning_rate': '9.706e-06', 'epoch': '1.126'}
|
| 287 |
+
{'loss': '0.6044', 'grad_norm': '5.068', 'learning_rate': '9.634e-06', 'epoch': '1.133'}
|
| 288 |
+
{'loss': '0.6007', 'grad_norm': '4.109', 'learning_rate': '9.562e-06', 'epoch': '1.139'}
|
| 289 |
+
{'loss': '0.5628', 'grad_norm': '4.954', 'learning_rate': '9.491e-06', 'epoch': '1.146'}
|
| 290 |
+
{'loss': '0.5732', 'grad_norm': '4.068', 'learning_rate': '9.419e-06', 'epoch': '1.152'}
|
| 291 |
+
{'loss': '0.5773', 'grad_norm': '4.939', 'learning_rate': '9.347e-06', 'epoch': '1.159'}
|
| 292 |
+
{'loss': '0.5719', 'grad_norm': '4.418', 'learning_rate': '9.275e-06', 'epoch': '1.165'}
|
| 293 |
+
2026-02-26 23:38:18 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 1.1653152059561382 after 36000 steps (truncated to 768):
|
| 294 |
+
2026-02-27 00:01:17 - Accuracy Cosine Similarity: 97.75%
|
| 295 |
+
2026-02-27 00:01:17 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 1.1653152059561382 after 36000 steps (truncated to 512):
|
| 296 |
+
2026-02-27 00:23:59 - Accuracy Cosine Similarity: 97.77%
|
| 297 |
+
2026-02-27 00:23:59 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 1.1653152059561382 after 36000 steps (truncated to 256):
|
| 298 |
+
2026-02-27 00:46:38 - Accuracy Cosine Similarity: 97.77%
|
| 299 |
+
2026-02-27 00:46:38 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 1.1653152059561382 after 36000 steps (truncated to 128):
|
| 300 |
+
2026-02-27 01:09:18 - Accuracy Cosine Similarity: 97.74%
|
| 301 |
+
2026-02-27 01:09:18 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 1.1653152059561382 after 36000 steps (truncated to 64):
|
| 302 |
+
2026-02-27 01:32:14 - Accuracy Cosine Similarity: 97.60%
|
| 303 |
+
{'eval_train_loss': '0.3356', 'eval_dev-768_cosine_accuracy': '0.9775', 'eval_dev-512_cosine_accuracy': '0.9777', 'eval_dev-256_cosine_accuracy': '0.9777', 'eval_dev-128_cosine_accuracy': '0.9774', 'eval_dev-64_cosine_accuracy': '0.976', 'eval_sequential_score': '0.9775', 'eval_train_runtime': '1.01e+04', 'eval_train_samples_per_second': '111.8', 'eval_train_steps_per_second': '13.98', 'epoch': '1.165'}
|
| 304 |
+
2026-02-27 01:32:14 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-36000
|
| 305 |
+
2026-02-27 01:32:14 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-36000
|
| 306 |
+
{'loss': '0.5471', 'grad_norm': '3.58', 'learning_rate': '9.203e-06', 'epoch': '1.172'}
|
| 307 |
+
{'loss': '0.5635', 'grad_norm': '5.198', 'learning_rate': '9.131e-06', 'epoch': '1.178'}
|
| 308 |
+
{'loss': '0.539', 'grad_norm': '4.468', 'learning_rate': '9.059e-06', 'epoch': '1.185'}
|
| 309 |
+
{'loss': '0.5428', 'grad_norm': '4.349', 'learning_rate': '8.987e-06', 'epoch': '1.191'}
|
| 310 |
+
{'loss': '0.5205', 'grad_norm': '2.936', 'learning_rate': '8.915e-06', 'epoch': '1.198'}
|
| 311 |
+
{'loss': '0.5362', 'grad_norm': '3.337', 'learning_rate': '8.843e-06', 'epoch': '1.204'}
|
| 312 |
+
{'loss': '0.5386', 'grad_norm': '5.76', 'learning_rate': '8.771e-06', 'epoch': '1.211'}
|
| 313 |
+
{'loss': '0.5203', 'grad_norm': '3.261', 'learning_rate': '8.699e-06', 'epoch': '1.217'}
|
| 314 |
+
{'loss': '0.5301', 'grad_norm': '3.732', 'learning_rate': '8.627e-06', 'epoch': '1.224'}
|
| 315 |
+
{'loss': '0.5232', 'grad_norm': '4.54', 'learning_rate': '8.555e-06', 'epoch': '1.23'}
|
| 316 |
+
{'loss': '0.4922', 'grad_norm': '4.291', 'learning_rate': '8.483e-06', 'epoch': '1.237'}
|
| 317 |
+
{'loss': '0.5029', 'grad_norm': '3.979', 'learning_rate': '8.412e-06', 'epoch': '1.243'}
|
| 318 |
+
{'loss': '0.4989', 'grad_norm': '7.829', 'learning_rate': '8.34e-06', 'epoch': '1.249'}
|
| 319 |
+
{'loss': '0.5053', 'grad_norm': '2.903', 'learning_rate': '8.268e-06', 'epoch': '1.256'}
|
| 320 |
+
{'loss': '0.5081', 'grad_norm': '5.471', 'learning_rate': '8.196e-06', 'epoch': '1.262'}
|
| 321 |
+
{'loss': '0.496', 'grad_norm': '5.204', 'learning_rate': '8.124e-06', 'epoch': '1.269'}
|
| 322 |
+
{'loss': '0.5052', 'grad_norm': '4.377', 'learning_rate': '8.052e-06', 'epoch': '1.275'}
|
| 323 |
+
{'loss': '0.4984', 'grad_norm': '4.184', 'learning_rate': '7.98e-06', 'epoch': '1.282'}
|
| 324 |
+
{'loss': '0.4909', 'grad_norm': '4.991', 'learning_rate': '7.908e-06', 'epoch': '1.288'}
|
| 325 |
+
{'loss': '0.512', 'grad_norm': '3.76', 'learning_rate': '7.836e-06', 'epoch': '1.295'}
|
| 326 |
+
{'loss': '0.4873', 'grad_norm': '3.844', 'learning_rate': '7.764e-06', 'epoch': '1.301'}
|
| 327 |
+
{'loss': '0.4896', 'grad_norm': '6.987', 'learning_rate': '7.692e-06', 'epoch': '1.308'}
|
| 328 |
+
{'loss': '0.49', 'grad_norm': '6.267', 'learning_rate': '7.62e-06', 'epoch': '1.314'}
|
| 329 |
+
{'loss': '0.5036', 'grad_norm': '3.776', 'learning_rate': '7.548e-06', 'epoch': '1.321'}
|
| 330 |
+
{'loss': '0.4876', 'grad_norm': '3.42', 'learning_rate': '7.476e-06', 'epoch': '1.327'}
|
| 331 |
+
{'loss': '0.4705', 'grad_norm': '5.478', 'learning_rate': '7.404e-06', 'epoch': '1.334'}
|
| 332 |
+
{'loss': '0.4786', 'grad_norm': '3.313', 'learning_rate': '7.333e-06', 'epoch': '1.34'}
|
| 333 |
+
{'loss': '0.4998', 'grad_norm': '3.13', 'learning_rate': '7.261e-06', 'epoch': '1.347'}
|
| 334 |
+
{'loss': '0.4692', 'grad_norm': '3.971', 'learning_rate': '7.189e-06', 'epoch': '1.353'}
|
| 335 |
+
{'loss': '0.5064', 'grad_norm': '6.238', 'learning_rate': '7.117e-06', 'epoch': '1.36'}
|
| 336 |
+
2026-02-27 03:24:31 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 1.3595371044751963 after 42000 steps (truncated to 768):
|
| 337 |
+
2026-02-27 03:47:24 - Accuracy Cosine Similarity: 97.88%
|
| 338 |
+
2026-02-27 03:47:24 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 1.3595371044751963 after 42000 steps (truncated to 512):
|
| 339 |
+
2026-02-27 04:10:18 - Accuracy Cosine Similarity: 97.90%
|
| 340 |
+
2026-02-27 04:10:18 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 1.3595371044751963 after 42000 steps (truncated to 256):
|
| 341 |
+
2026-02-27 04:33:12 - Accuracy Cosine Similarity: 97.90%
|
| 342 |
+
2026-02-27 04:33:12 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 1.3595371044751963 after 42000 steps (truncated to 128):
|
| 343 |
+
2026-02-27 04:56:07 - Accuracy Cosine Similarity: 97.85%
|
| 344 |
+
2026-02-27 04:56:07 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 1.3595371044751963 after 42000 steps (truncated to 64):
|
| 345 |
+
2026-02-27 05:19:11 - Accuracy Cosine Similarity: 97.74%
|
| 346 |
+
{'eval_train_loss': '0.316', 'eval_dev-768_cosine_accuracy': '0.9788', 'eval_dev-512_cosine_accuracy': '0.979', 'eval_dev-256_cosine_accuracy': '0.979', 'eval_dev-128_cosine_accuracy': '0.9785', 'eval_dev-64_cosine_accuracy': '0.9774', 'eval_sequential_score': '0.9788', 'eval_train_runtime': '1.014e+04', 'eval_train_samples_per_second': '111.5', 'eval_train_steps_per_second': '13.93', 'epoch': '1.36'}
|
| 347 |
+
2026-02-27 05:19:11 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-42000
|
| 348 |
+
2026-02-27 05:19:11 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-42000
|
| 349 |
+
{'loss': '0.4925', 'grad_norm': '5.158', 'learning_rate': '7.045e-06', 'epoch': '1.366'}
|
| 350 |
+
{'loss': '0.4601', 'grad_norm': '4.139', 'learning_rate': '6.973e-06', 'epoch': '1.372'}
|
| 351 |
+
{'loss': '0.4762', 'grad_norm': '3.411', 'learning_rate': '6.901e-06', 'epoch': '1.379'}
|
| 352 |
+
{'loss': '0.4986', 'grad_norm': '4.23', 'learning_rate': '6.829e-06', 'epoch': '1.385'}
|
| 353 |
+
{'loss': '0.4656', 'grad_norm': '5.326', 'learning_rate': '6.757e-06', 'epoch': '1.392'}
|
| 354 |
+
{'loss': '0.4507', 'grad_norm': '3.826', 'learning_rate': '6.685e-06', 'epoch': '1.398'}
|
| 355 |
+
{'loss': '0.4862', 'grad_norm': '3.509', 'learning_rate': '6.613e-06', 'epoch': '1.405'}
|
| 356 |
+
{'loss': '0.4596', 'grad_norm': '4.734', 'learning_rate': '6.541e-06', 'epoch': '1.411'}
|
| 357 |
+
{'loss': '0.4696', 'grad_norm': '4.799', 'learning_rate': '6.469e-06', 'epoch': '1.418'}
|
| 358 |
+
{'loss': '0.4925', 'grad_norm': '4.942', 'learning_rate': '6.397e-06', 'epoch': '1.424'}
|
| 359 |
+
{'loss': '0.4796', 'grad_norm': '4.147', 'learning_rate': '6.325e-06', 'epoch': '1.431'}
|
| 360 |
+
{'loss': '0.4525', 'grad_norm': '5.146', 'learning_rate': '6.254e-06', 'epoch': '1.437'}
|
| 361 |
+
{'loss': '0.4717', 'grad_norm': '3.52', 'learning_rate': '6.182e-06', 'epoch': '1.444'}
|
| 362 |
+
{'loss': '0.4803', 'grad_norm': '3.25', 'learning_rate': '6.11e-06', 'epoch': '1.45'}
|
| 363 |
+
{'loss': '0.4675', 'grad_norm': '7.35', 'learning_rate': '6.038e-06', 'epoch': '1.457'}
|
| 364 |
+
{'loss': '0.4631', 'grad_norm': '3.847', 'learning_rate': '5.966e-06', 'epoch': '1.463'}
|
| 365 |
+
{'loss': '0.4622', 'grad_norm': '4.57', 'learning_rate': '5.894e-06', 'epoch': '1.47'}
|
| 366 |
+
{'loss': '0.4496', 'grad_norm': '1.997', 'learning_rate': '5.822e-06', 'epoch': '1.476'}
|
| 367 |
+
{'loss': '0.4678', 'grad_norm': '4.266', 'learning_rate': '5.75e-06', 'epoch': '1.483'}
|
| 368 |
+
{'loss': '0.4495', 'grad_norm': '5.948', 'learning_rate': '5.678e-06', 'epoch': '1.489'}
|
| 369 |
+
{'loss': '0.4474', 'grad_norm': '3.7', 'learning_rate': '5.606e-06', 'epoch': '1.495'}
|
| 370 |
+
{'loss': '0.4587', 'grad_norm': '2.877', 'learning_rate': '5.534e-06', 'epoch': '1.502'}
|
| 371 |
+
{'loss': '0.4591', 'grad_norm': '4.245', 'learning_rate': '5.462e-06', 'epoch': '1.508'}
|
| 372 |
+
{'loss': '0.4573', 'grad_norm': '5.431', 'learning_rate': '5.39e-06', 'epoch': '1.515'}
|
| 373 |
+
{'loss': '0.4442', 'grad_norm': '3.338', 'learning_rate': '5.318e-06', 'epoch': '1.521'}
|
| 374 |
+
{'loss': '0.455', 'grad_norm': '4.723', 'learning_rate': '5.246e-06', 'epoch': '1.528'}
|
| 375 |
+
{'loss': '0.4493', 'grad_norm': '4.226', 'learning_rate': '5.175e-06', 'epoch': '1.534'}
|
| 376 |
+
{'loss': '0.4485', 'grad_norm': '4.451', 'learning_rate': '5.103e-06', 'epoch': '1.541'}
|
| 377 |
+
{'loss': '0.4569', 'grad_norm': '4.297', 'learning_rate': '5.031e-06', 'epoch': '1.547'}
|
| 378 |
+
{'loss': '0.4346', 'grad_norm': '4.199', 'learning_rate': '4.959e-06', 'epoch': '1.554'}
|
| 379 |
+
2026-02-27 07:11:49 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 1.5537590029942543 after 48000 steps (truncated to 768):
|
| 380 |
+
2026-02-27 07:34:37 - Accuracy Cosine Similarity: 97.99%
|
| 381 |
+
2026-02-27 07:34:37 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 1.5537590029942543 after 48000 steps (truncated to 512):
|
| 382 |
+
2026-02-27 07:57:13 - Accuracy Cosine Similarity: 98.02%
|
| 383 |
+
2026-02-27 07:57:13 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 1.5537590029942543 after 48000 steps (truncated to 256):
|
| 384 |
+
2026-02-27 08:20:07 - Accuracy Cosine Similarity: 98.02%
|
| 385 |
+
2026-02-27 08:20:07 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 1.5537590029942543 after 48000 steps (truncated to 128):
|
| 386 |
+
2026-02-27 08:42:52 - Accuracy Cosine Similarity: 97.98%
|
| 387 |
+
2026-02-27 08:42:52 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 1.5537590029942543 after 48000 steps (truncated to 64):
|
| 388 |
+
2026-02-27 09:05:32 - Accuracy Cosine Similarity: 97.88%
|
| 389 |
+
{'eval_train_loss': '0.3001', 'eval_dev-768_cosine_accuracy': '0.9799', 'eval_dev-512_cosine_accuracy': '0.9802', 'eval_dev-256_cosine_accuracy': '0.9802', 'eval_dev-128_cosine_accuracy': '0.9798', 'eval_dev-64_cosine_accuracy': '0.9788', 'eval_sequential_score': '0.9799', 'eval_train_runtime': '1.008e+04', 'eval_train_samples_per_second': '112.1', 'eval_train_steps_per_second': '14.02', 'epoch': '1.554'}
|
| 390 |
+
2026-02-27 09:05:32 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-48000
|
| 391 |
+
2026-02-27 09:05:32 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-48000
|
| 392 |
+
{'loss': '0.4469', 'grad_norm': '3.364', 'learning_rate': '4.887e-06', 'epoch': '1.56'}
|
| 393 |
+
{'loss': '0.4602', 'grad_norm': '5.309', 'learning_rate': '4.815e-06', 'epoch': '1.567'}
|
| 394 |
+
{'loss': '0.443', 'grad_norm': '3.875', 'learning_rate': '4.743e-06', 'epoch': '1.573'}
|
| 395 |
+
{'loss': '0.4524', 'grad_norm': '4.824', 'learning_rate': '4.671e-06', 'epoch': '1.58'}
|
| 396 |
+
{'loss': '0.4528', 'grad_norm': '4.996', 'learning_rate': '4.599e-06', 'epoch': '1.586'}
|
| 397 |
+
{'loss': '0.4348', 'grad_norm': '4.96', 'learning_rate': '4.527e-06', 'epoch': '1.593'}
|
| 398 |
+
{'loss': '0.4533', 'grad_norm': '5.219', 'learning_rate': '4.455e-06', 'epoch': '1.599'}
|
| 399 |
+
{'loss': '0.4523', 'grad_norm': '3.444', 'learning_rate': '4.383e-06', 'epoch': '1.606'}
|
| 400 |
+
{'loss': '0.4509', 'grad_norm': '5.647', 'learning_rate': '4.311e-06', 'epoch': '1.612'}
|
| 401 |
+
{'loss': '0.4365', 'grad_norm': '5.052', 'learning_rate': '4.239e-06', 'epoch': '1.618'}
|
| 402 |
+
{'loss': '0.4504', 'grad_norm': '5.786', 'learning_rate': '4.167e-06', 'epoch': '1.625'}
|
| 403 |
+
{'loss': '0.4292', 'grad_norm': '4.353', 'learning_rate': '4.096e-06', 'epoch': '1.631'}
|
| 404 |
+
{'loss': '0.4406', 'grad_norm': '2.976', 'learning_rate': '4.024e-06', 'epoch': '1.638'}
|
| 405 |
+
{'loss': '0.4333', 'grad_norm': '3.685', 'learning_rate': '3.952e-06', 'epoch': '1.644'}
|
| 406 |
+
{'loss': '0.4361', 'grad_norm': '4.107', 'learning_rate': '3.88e-06', 'epoch': '1.651'}
|
| 407 |
+
{'loss': '0.4065', 'grad_norm': '3.636', 'learning_rate': '3.808e-06', 'epoch': '1.657'}
|
| 408 |
+
{'loss': '0.4671', 'grad_norm': '3.464', 'learning_rate': '3.736e-06', 'epoch': '1.664'}
|
| 409 |
+
{'loss': '0.4328', 'grad_norm': '3.129', 'learning_rate': '3.664e-06', 'epoch': '1.67'}
|
| 410 |
+
{'loss': '0.431', 'grad_norm': '2.453', 'learning_rate': '3.592e-06', 'epoch': '1.677'}
|
| 411 |
+
{'loss': '0.4523', 'grad_norm': '3.727', 'learning_rate': '3.52e-06', 'epoch': '1.683'}
|
| 412 |
+
{'loss': '0.4232', 'grad_norm': '4.398', 'learning_rate': '3.448e-06', 'epoch': '1.69'}
|
| 413 |
+
{'loss': '0.4257', 'grad_norm': '2.861', 'learning_rate': '3.376e-06', 'epoch': '1.696'}
|
| 414 |
+
{'loss': '0.4448', 'grad_norm': '3.523', 'learning_rate': '3.304e-06', 'epoch': '1.703'}
|
| 415 |
+
{'loss': '0.4491', 'grad_norm': '3.893', 'learning_rate': '3.232e-06', 'epoch': '1.709'}
|
| 416 |
+
{'loss': '0.4224', 'grad_norm': '3.399', 'learning_rate': '3.16e-06', 'epoch': '1.716'}
|
| 417 |
+
{'loss': '0.4297', 'grad_norm': '4.703', 'learning_rate': '3.088e-06', 'epoch': '1.722'}
|
| 418 |
+
{'loss': '0.4522', 'grad_norm': '4.29', 'learning_rate': '3.017e-06', 'epoch': '1.729'}
|
| 419 |
+
{'loss': '0.4195', 'grad_norm': '4.29', 'learning_rate': '2.945e-06', 'epoch': '1.735'}
|
| 420 |
+
{'loss': '0.4227', 'grad_norm': '3.841', 'learning_rate': '2.873e-06', 'epoch': '1.742'}
|
| 421 |
+
{'loss': '0.4381', 'grad_norm': '4.086', 'learning_rate': '2.801e-06', 'epoch': '1.748'}
|
| 422 |
+
2026-02-27 10:59:10 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 1.7479809015133123 after 54000 steps (truncated to 768):
|
| 423 |
+
2026-02-27 11:22:08 - Accuracy Cosine Similarity: 98.07%
|
| 424 |
+
2026-02-27 11:22:08 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 1.7479809015133123 after 54000 steps (truncated to 512):
|
| 425 |
+
2026-02-27 11:44:57 - Accuracy Cosine Similarity: 98.08%
|
| 426 |
+
2026-02-27 11:44:57 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 1.7479809015133123 after 54000 steps (truncated to 256):
|
| 427 |
+
2026-02-27 12:07:55 - Accuracy Cosine Similarity: 98.08%
|
| 428 |
+
2026-02-27 12:07:55 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 1.7479809015133123 after 54000 steps (truncated to 128):
|
| 429 |
+
2026-02-27 12:30:35 - Accuracy Cosine Similarity: 98.05%
|
| 430 |
+
2026-02-27 12:30:35 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 1.7479809015133123 after 54000 steps (truncated to 64):
|
| 431 |
+
2026-02-27 12:53:24 - Accuracy Cosine Similarity: 97.94%
|
| 432 |
+
{'eval_train_loss': '0.2875', 'eval_dev-768_cosine_accuracy': '0.9807', 'eval_dev-512_cosine_accuracy': '0.9808', 'eval_dev-256_cosine_accuracy': '0.9808', 'eval_dev-128_cosine_accuracy': '0.9805', 'eval_dev-64_cosine_accuracy': '0.9794', 'eval_sequential_score': '0.9807', 'eval_train_runtime': '1.012e+04', 'eval_train_samples_per_second': '111.6', 'eval_train_steps_per_second': '13.95', 'epoch': '1.748'}
|
| 433 |
+
2026-02-27 12:53:24 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-54000
|
| 434 |
+
2026-02-27 12:53:24 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-54000
|
| 435 |
+
{'loss': '0.446', 'grad_norm': '4.176', 'learning_rate': '2.729e-06', 'epoch': '1.754'}
|
| 436 |
+
{'loss': '0.426', 'grad_norm': '4.261', 'learning_rate': '2.657e-06', 'epoch': '1.761'}
|
| 437 |
+
{'loss': '0.4299', 'grad_norm': '4.676', 'learning_rate': '2.585e-06', 'epoch': '1.767'}
|
| 438 |
+
{'loss': '0.4247', 'grad_norm': '3.933', 'learning_rate': '2.513e-06', 'epoch': '1.774'}
|
| 439 |
+
{'loss': '0.4244', 'grad_norm': '4.853', 'learning_rate': '2.441e-06', 'epoch': '1.78'}
|
| 440 |
+
{'loss': '0.4185', 'grad_norm': '2.985', 'learning_rate': '2.369e-06', 'epoch': '1.787'}
|
| 441 |
+
{'loss': '0.4292', 'grad_norm': '3.804', 'learning_rate': '2.297e-06', 'epoch': '1.793'}
|
| 442 |
+
{'loss': '0.4468', 'grad_norm': '3.187', 'learning_rate': '2.225e-06', 'epoch': '1.8'}
|
| 443 |
+
{'loss': '0.4118', 'grad_norm': '4.004', 'learning_rate': '2.153e-06', 'epoch': '1.806'}
|
| 444 |
+
{'loss': '0.4306', 'grad_norm': '4.007', 'learning_rate': '2.081e-06', 'epoch': '1.813'}
|
| 445 |
+
{'loss': '0.4447', 'grad_norm': '4.323', 'learning_rate': '2.009e-06', 'epoch': '1.819'}
|
| 446 |
+
{'loss': '0.4147', 'grad_norm': '3.863', 'learning_rate': '1.938e-06', 'epoch': '1.826'}
|
| 447 |
+
{'loss': '0.4189', 'grad_norm': '4.788', 'learning_rate': '1.866e-06', 'epoch': '1.832'}
|
| 448 |
+
{'loss': '0.4167', 'grad_norm': '4.276', 'learning_rate': '1.794e-06', 'epoch': '1.839'}
|
| 449 |
+
{'loss': '0.4022', 'grad_norm': '3.887', 'learning_rate': '1.722e-06', 'epoch': '1.845'}
|
| 450 |
+
{'loss': '0.4158', 'grad_norm': '3.075', 'learning_rate': '1.65e-06', 'epoch': '1.852'}
|
| 451 |
+
{'loss': '0.4228', 'grad_norm': '3.993', 'learning_rate': '1.578e-06', 'epoch': '1.858'}
|
| 452 |
+
{'loss': '0.4256', 'grad_norm': '4.497', 'learning_rate': '1.506e-06', 'epoch': '1.865'}
|
| 453 |
+
{'loss': '0.4251', 'grad_norm': '4.539', 'learning_rate': '1.434e-06', 'epoch': '1.871'}
|
| 454 |
+
{'loss': '0.4232', 'grad_norm': '2.337', 'learning_rate': '1.362e-06', 'epoch': '1.877'}
|
| 455 |
+
{'loss': '0.4143', 'grad_norm': '3.389', 'learning_rate': '1.29e-06', 'epoch': '1.884'}
|
| 456 |
+
{'loss': '0.4331', 'grad_norm': '3.545', 'learning_rate': '1.218e-06', 'epoch': '1.89'}
|
| 457 |
+
{'loss': '0.4253', 'grad_norm': '5.606', 'learning_rate': '1.146e-06', 'epoch': '1.897'}
|
| 458 |
+
{'loss': '0.441', 'grad_norm': '4.453', 'learning_rate': '1.074e-06', 'epoch': '1.903'}
|
| 459 |
+
{'loss': '0.4337', 'grad_norm': '5.374', 'learning_rate': '1.002e-06', 'epoch': '1.91'}
|
| 460 |
+
{'loss': '0.4016', 'grad_norm': '2.246', 'learning_rate': '9.305e-07', 'epoch': '1.916'}
|
| 461 |
+
{'loss': '0.4249', 'grad_norm': '5.255', 'learning_rate': '8.585e-07', 'epoch': '1.923'}
|
| 462 |
+
{'loss': '0.4108', 'grad_norm': '3.59', 'learning_rate': '7.866e-07', 'epoch': '1.929'}
|
| 463 |
+
{'loss': '0.4272', 'grad_norm': '4.258', 'learning_rate': '7.147e-07', 'epoch': '1.936'}
|
| 464 |
+
{'loss': '0.3916', 'grad_norm': '3.476', 'learning_rate': '6.427e-07', 'epoch': '1.942'}
|
| 465 |
+
2026-02-27 14:47:29 - TripletEvaluator: Evaluating the model on the dev-768 dataset in epoch 1.9422028000323703 after 60000 steps (truncated to 768):
|
| 466 |
+
2026-02-27 15:10:59 - Accuracy Cosine Similarity: 98.10%
|
| 467 |
+
2026-02-27 15:10:59 - TripletEvaluator: Evaluating the model on the dev-512 dataset in epoch 1.9422028000323703 after 60000 steps (truncated to 512):
|
| 468 |
+
2026-02-27 15:34:30 - Accuracy Cosine Similarity: 98.11%
|
| 469 |
+
2026-02-27 15:34:30 - TripletEvaluator: Evaluating the model on the dev-256 dataset in epoch 1.9422028000323703 after 60000 steps (truncated to 256):
|
| 470 |
+
2026-02-27 15:58:10 - Accuracy Cosine Similarity: 98.13%
|
| 471 |
+
2026-02-27 15:58:10 - TripletEvaluator: Evaluating the model on the dev-128 dataset in epoch 1.9422028000323703 after 60000 steps (truncated to 128):
|
| 472 |
+
2026-02-27 16:21:18 - Accuracy Cosine Similarity: 98.11%
|
| 473 |
+
2026-02-27 16:21:18 - TripletEvaluator: Evaluating the model on the dev-64 dataset in epoch 1.9422028000323703 after 60000 steps (truncated to 64):
|
| 474 |
+
2026-02-27 16:44:14 - Accuracy Cosine Similarity: 97.97%
|
| 475 |
+
{'eval_train_loss': '0.2812', 'eval_dev-768_cosine_accuracy': '0.981', 'eval_dev-512_cosine_accuracy': '0.9811', 'eval_dev-256_cosine_accuracy': '0.9813', 'eval_dev-128_cosine_accuracy': '0.9811', 'eval_dev-64_cosine_accuracy': '0.9797', 'eval_sequential_score': '0.981', 'eval_train_runtime': '1.03e+04', 'eval_train_samples_per_second': '109.7', 'eval_train_steps_per_second': '13.71', 'epoch': '1.942'}
|
| 476 |
+
2026-02-27 16:44:14 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-60000
|
| 477 |
+
2026-02-27 16:44:14 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-60000
|
| 478 |
+
{'loss': '0.4334', 'grad_norm': '4.623', 'learning_rate': '5.708e-07', 'epoch': '1.949'}
|
| 479 |
+
{'loss': '0.4462', 'grad_norm': '5.31', 'learning_rate': '4.989e-07', 'epoch': '1.955'}
|
| 480 |
+
{'loss': '0.4436', 'grad_norm': '3.379', 'learning_rate': '4.269e-07', 'epoch': '1.962'}
|
| 481 |
+
{'loss': '0.4278', 'grad_norm': '5.471', 'learning_rate': '3.55e-07', 'epoch': '1.968'}
|
| 482 |
+
{'loss': '0.417', 'grad_norm': '3.435', 'learning_rate': '2.831e-07', 'epoch': '1.975'}
|
| 483 |
+
{'loss': '0.4376', 'grad_norm': '2.617', 'learning_rate': '2.111e-07', 'epoch': '1.981'}
|
| 484 |
+
{'loss': '0.4433', 'grad_norm': '3.465', 'learning_rate': '1.392e-07', 'epoch': '1.988'}
|
| 485 |
+
{'loss': '0.4292', 'grad_norm': '2.354', 'learning_rate': '6.726e-08', 'epoch': '1.994'}
|
| 486 |
+
2026-02-27 17:01:56 - Saving model checkpoint to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-61786
|
| 487 |
+
2026-02-27 17:01:56 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-61786
|
| 488 |
+
{'train_runtime': '9.588e+04', 'train_samples_per_second': '82.48', 'train_steps_per_second': '0.644', 'train_loss': '0.403', 'epoch': '2'}
|
| 489 |
+
2026-02-27 17:01:58 - Save model to /home/skiredj.abderrahman/khalil/sbert_training/output/final
|
| 490 |
+
model saved successfully
|
| 491 |
+
2026-02-27 17:01:59 - TripletEvaluator: Evaluating the model on the test-768 dataset (truncated to 768):
|
| 492 |
+
2026-02-27 17:21:39 - Accuracy Cosine Similarity: 98.10%
|
| 493 |
+
2026-02-27 17:21:39 - TripletEvaluator: Evaluating the model on the test-512 dataset (truncated to 512):
|
| 494 |
+
2026-02-27 17:41:10 - Accuracy Cosine Similarity: 98.13%
|
| 495 |
+
2026-02-27 17:41:10 - TripletEvaluator: Evaluating the model on the test-256 dataset (truncated to 256):
|
| 496 |
+
2026-02-27 18:00:40 - Accuracy Cosine Similarity: 98.13%
|
| 497 |
+
2026-02-27 18:00:40 - TripletEvaluator: Evaluating the model on the test-128 dataset (truncated to 128):
|
| 498 |
+
2026-02-27 18:20:06 - Accuracy Cosine Similarity: 98.11%
|
| 499 |
+
2026-02-27 18:20:06 - TripletEvaluator: Evaluating the model on the test-64 dataset (truncated to 64):
|
| 500 |
+
2026-02-27 18:39:32 - Accuracy Cosine Similarity: 97.97%
|
epoch2/model/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 768,
|
| 3 |
+
"pooling_mode_cls_token": false,
|
| 4 |
+
"pooling_mode_mean_tokens": true,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
epoch2/model/README.md
ADDED
|
@@ -0,0 +1,773 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- sentence-similarity
|
| 5 |
+
- feature-extraction
|
| 6 |
+
- dense
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
- dataset_size:3954179
|
| 9 |
+
- loss:MatryoshkaLoss
|
| 10 |
+
- loss:MultipleNegativesRankingLoss
|
| 11 |
+
widget:
|
| 12 |
+
- source_sentence: إذا لم تكن قد فعلت ذلك بالفعل ، تحقق من تصميمنا الجديد للمراسلات
|
| 13 |
+
والحوارات واليوميات .
|
| 14 |
+
sentences:
|
| 15 |
+
- تم إعادة تصميم الرسائل والحوارات .
|
| 16 |
+
- يقدم مقهى بارج كل من وجبات الغداء والإفطار .
|
| 17 |
+
- قبل ان نعرف اسماء بعضنا او اي شيء قد تعانقنا وبكىنا .
|
| 18 |
+
- source_sentence: أين تقع جامعة واينزبرج
|
| 19 |
+
sentences:
|
| 20 |
+
- جامعة دالاس بابتيست ( DBU ) ، المعروفة سابقا باسم كلية دالاس بابتيست ، هي جامعة
|
| 21 |
+
فنون ليبرالية مسيحية تقع في دالاس ، تكساس . يقع الحرم الجامعي الرئيسي على بعد
|
| 22 |
+
حوالي 12 ميلا ( 19 كم ) جنوب غرب وسط مدينة دالاس ويطل على بحيرة ماونتين كريك .
|
| 23 |
+
تأسست جامعة دالاس بابتيست عام 1898 باسم كلية ديكاتور بابتيست ، وتدير حاليا حرما
|
| 24 |
+
جامعيا في دالاس وبلانو وهيرست .
|
| 25 |
+
- الزوجان معا
|
| 26 |
+
- تقع جامعة واينسبرغ في حرم جامعي معاصر في تلال جنوب غرب ولاية بنسلفانيا ، مع ثلاثة
|
| 27 |
+
مراكز للبالغين تقع في مناطق بيتسبرغ في ساوثبوينت وكرانبيري ومونروفيل . تم إدراج
|
| 28 |
+
Hanna Hall و Miller Hall في السجل الوطني للأماكن التاريخية .
|
| 29 |
+
- source_sentence: The isolated Russian forces resisted in several areas for two more
|
| 30 |
+
days .
|
| 31 |
+
sentences:
|
| 32 |
+
- 'ياهو : كيف يمكنني معرفة ما إذا كان البريد الإلكتروني الذي أرسلته قد تم استلامه
|
| 33 |
+
أو قراءته ؟'
|
| 34 |
+
- واستمرت الاشتباكات الحدودية خلال اليومين المقبلين ، حيث استهدفت المخافر الحدودية
|
| 35 |
+
من الجانبين والتي أسفرت عن وقوع عشرات الإصابات .
|
| 36 |
+
- قاومت القوات الروسية المعزولة في عة مناطق لمدة يومين آخرين .
|
| 37 |
+
- source_sentence: فتاة هيبي بشعر أشقر وأرجواني على الجانب يرتدي قميص أبيض وملابس
|
| 38 |
+
سوداء
|
| 39 |
+
sentences:
|
| 40 |
+
- فتاة " هيبي " ترتدي قميصا أبيضا وملابس سوداء شعرها أشقر وأحمر
|
| 41 |
+
- المرأة تضع يدها في جيب الرجل
|
| 42 |
+
- فتاة لديها سترة حمراء وسوداء
|
| 43 |
+
- source_sentence: رجل وامرأة يجلسان في سيارة ووجههما في الاتجاه المعاكس من الكاميرا
|
| 44 |
+
sentences:
|
| 45 |
+
- هناك شخصان وسيارة
|
| 46 |
+
- سيارة صدئة هي الشيء الوحيد المرئي
|
| 47 |
+
- كان أفضل حالا
|
| 48 |
+
pipeline_tag: sentence-similarity
|
| 49 |
+
library_name: sentence-transformers
|
| 50 |
+
metrics:
|
| 51 |
+
- cosine_accuracy
|
| 52 |
+
model-index:
|
| 53 |
+
- name: SentenceTransformer
|
| 54 |
+
results:
|
| 55 |
+
- task:
|
| 56 |
+
type: triplet
|
| 57 |
+
name: Triplet
|
| 58 |
+
dataset:
|
| 59 |
+
name: dev 768
|
| 60 |
+
type: dev-768
|
| 61 |
+
metrics:
|
| 62 |
+
- type: cosine_accuracy
|
| 63 |
+
value: 0.9809960126876831
|
| 64 |
+
name: Cosine Accuracy
|
| 65 |
+
- task:
|
| 66 |
+
type: triplet
|
| 67 |
+
name: Triplet
|
| 68 |
+
dataset:
|
| 69 |
+
name: dev 512
|
| 70 |
+
type: dev-512
|
| 71 |
+
metrics:
|
| 72 |
+
- type: cosine_accuracy
|
| 73 |
+
value: 0.9811199903488159
|
| 74 |
+
name: Cosine Accuracy
|
| 75 |
+
- task:
|
| 76 |
+
type: triplet
|
| 77 |
+
name: Triplet
|
| 78 |
+
dataset:
|
| 79 |
+
name: dev 256
|
| 80 |
+
type: dev-256
|
| 81 |
+
metrics:
|
| 82 |
+
- type: cosine_accuracy
|
| 83 |
+
value: 0.9813200235366821
|
| 84 |
+
name: Cosine Accuracy
|
| 85 |
+
- task:
|
| 86 |
+
type: triplet
|
| 87 |
+
name: Triplet
|
| 88 |
+
dataset:
|
| 89 |
+
name: dev 128
|
| 90 |
+
type: dev-128
|
| 91 |
+
metrics:
|
| 92 |
+
- type: cosine_accuracy
|
| 93 |
+
value: 0.9811360239982605
|
| 94 |
+
name: Cosine Accuracy
|
| 95 |
+
- task:
|
| 96 |
+
type: triplet
|
| 97 |
+
name: Triplet
|
| 98 |
+
dataset:
|
| 99 |
+
name: dev 64
|
| 100 |
+
type: dev-64
|
| 101 |
+
metrics:
|
| 102 |
+
- type: cosine_accuracy
|
| 103 |
+
value: 0.9796760082244873
|
| 104 |
+
name: Cosine Accuracy
|
| 105 |
+
---
|
| 106 |
+
|
| 107 |
+
# SentenceTransformer
|
| 108 |
+
|
| 109 |
+
This is a [sentence-transformers](https://www.SBERT.net) model trained on the train dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 110 |
+
|
| 111 |
+
## Model Details
|
| 112 |
+
|
| 113 |
+
### Model Description
|
| 114 |
+
- **Model Type:** Sentence Transformer
|
| 115 |
+
<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
|
| 116 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 117 |
+
- **Output Dimensionality:** 768 dimensions
|
| 118 |
+
- **Similarity Function:** Cosine Similarity
|
| 119 |
+
- **Training Dataset:**
|
| 120 |
+
- train
|
| 121 |
+
<!-- - **Language:** Unknown -->
|
| 122 |
+
<!-- - **License:** Unknown -->
|
| 123 |
+
|
| 124 |
+
### Model Sources
|
| 125 |
+
|
| 126 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 127 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
|
| 128 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 129 |
+
|
| 130 |
+
### Full Model Architecture
|
| 131 |
+
|
| 132 |
+
```
|
| 133 |
+
SentenceTransformer(
|
| 134 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
|
| 135 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
| 136 |
+
)
|
| 137 |
+
```
|
| 138 |
+
|
| 139 |
+
## Usage
|
| 140 |
+
|
| 141 |
+
### Direct Usage (Sentence Transformers)
|
| 142 |
+
|
| 143 |
+
First install the Sentence Transformers library:
|
| 144 |
+
|
| 145 |
+
```bash
|
| 146 |
+
pip install -U sentence-transformers
|
| 147 |
+
```
|
| 148 |
+
|
| 149 |
+
Then you can load this model and run inference.
|
| 150 |
+
```python
|
| 151 |
+
from sentence_transformers import SentenceTransformer
|
| 152 |
+
|
| 153 |
+
# Download from the 🤗 Hub
|
| 154 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 155 |
+
# Run inference
|
| 156 |
+
sentences = [
|
| 157 |
+
'رجل وامرأة يجلسان في سيارة ووجههما في الاتجاه المعاكس من الكاميرا',
|
| 158 |
+
'هناك شخصان وسيارة',
|
| 159 |
+
'سيارة صدئة هي الشيء الوحيد المرئي',
|
| 160 |
+
]
|
| 161 |
+
embeddings = model.encode(sentences)
|
| 162 |
+
print(embeddings.shape)
|
| 163 |
+
# [3, 768]
|
| 164 |
+
|
| 165 |
+
# Get the similarity scores for the embeddings
|
| 166 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 167 |
+
print(similarities)
|
| 168 |
+
# tensor([[1.0000, 0.6451, 0.3299],
|
| 169 |
+
# [0.6451, 1.0000, 0.4022],
|
| 170 |
+
# [0.3299, 0.4022, 1.0000]])
|
| 171 |
+
```
|
| 172 |
+
|
| 173 |
+
<!--
|
| 174 |
+
### Direct Usage (Transformers)
|
| 175 |
+
|
| 176 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 177 |
+
|
| 178 |
+
</details>
|
| 179 |
+
-->
|
| 180 |
+
|
| 181 |
+
<!--
|
| 182 |
+
### Downstream Usage (Sentence Transformers)
|
| 183 |
+
|
| 184 |
+
You can finetune this model on your own dataset.
|
| 185 |
+
|
| 186 |
+
<details><summary>Click to expand</summary>
|
| 187 |
+
|
| 188 |
+
</details>
|
| 189 |
+
-->
|
| 190 |
+
|
| 191 |
+
<!--
|
| 192 |
+
### Out-of-Scope Use
|
| 193 |
+
|
| 194 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 195 |
+
-->
|
| 196 |
+
|
| 197 |
+
## Evaluation
|
| 198 |
+
|
| 199 |
+
### Metrics
|
| 200 |
+
|
| 201 |
+
#### Triplet
|
| 202 |
+
|
| 203 |
+
* Dataset: `dev-768`
|
| 204 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
|
| 205 |
+
```json
|
| 206 |
+
{
|
| 207 |
+
"truncate_dim": 768
|
| 208 |
+
}
|
| 209 |
+
```
|
| 210 |
+
|
| 211 |
+
| Metric | Value |
|
| 212 |
+
|:--------------------|:----------|
|
| 213 |
+
| **cosine_accuracy** | **0.981** |
|
| 214 |
+
|
| 215 |
+
#### Triplet
|
| 216 |
+
|
| 217 |
+
* Dataset: `dev-512`
|
| 218 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
|
| 219 |
+
```json
|
| 220 |
+
{
|
| 221 |
+
"truncate_dim": 512
|
| 222 |
+
}
|
| 223 |
+
```
|
| 224 |
+
|
| 225 |
+
| Metric | Value |
|
| 226 |
+
|:--------------------|:-----------|
|
| 227 |
+
| **cosine_accuracy** | **0.9811** |
|
| 228 |
+
|
| 229 |
+
#### Triplet
|
| 230 |
+
|
| 231 |
+
* Dataset: `dev-256`
|
| 232 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
|
| 233 |
+
```json
|
| 234 |
+
{
|
| 235 |
+
"truncate_dim": 256
|
| 236 |
+
}
|
| 237 |
+
```
|
| 238 |
+
|
| 239 |
+
| Metric | Value |
|
| 240 |
+
|:--------------------|:-----------|
|
| 241 |
+
| **cosine_accuracy** | **0.9813** |
|
| 242 |
+
|
| 243 |
+
#### Triplet
|
| 244 |
+
|
| 245 |
+
* Dataset: `dev-128`
|
| 246 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
|
| 247 |
+
```json
|
| 248 |
+
{
|
| 249 |
+
"truncate_dim": 128
|
| 250 |
+
}
|
| 251 |
+
```
|
| 252 |
+
|
| 253 |
+
| Metric | Value |
|
| 254 |
+
|:--------------------|:-----------|
|
| 255 |
+
| **cosine_accuracy** | **0.9811** |
|
| 256 |
+
|
| 257 |
+
#### Triplet
|
| 258 |
+
|
| 259 |
+
* Dataset: `dev-64`
|
| 260 |
+
* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
|
| 261 |
+
```json
|
| 262 |
+
{
|
| 263 |
+
"truncate_dim": 64
|
| 264 |
+
}
|
| 265 |
+
```
|
| 266 |
+
|
| 267 |
+
| Metric | Value |
|
| 268 |
+
|:--------------------|:-----------|
|
| 269 |
+
| **cosine_accuracy** | **0.9797** |
|
| 270 |
+
|
| 271 |
+
<!--
|
| 272 |
+
## Bias, Risks and Limitations
|
| 273 |
+
|
| 274 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 275 |
+
-->
|
| 276 |
+
|
| 277 |
+
<!--
|
| 278 |
+
### Recommendations
|
| 279 |
+
|
| 280 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 281 |
+
-->
|
| 282 |
+
|
| 283 |
+
## Training Details
|
| 284 |
+
|
| 285 |
+
### Training Dataset
|
| 286 |
+
|
| 287 |
+
#### train
|
| 288 |
+
|
| 289 |
+
* Dataset: train
|
| 290 |
+
* Size: 3,954,179 training samples
|
| 291 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 292 |
+
* Approximate statistics based on the first 1000 samples:
|
| 293 |
+
| | anchor | positive | negative |
|
| 294 |
+
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
| 295 |
+
| type | string | string | string |
|
| 296 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 16.1 tokens</li><li>max: 113 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 41.85 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 41.99 tokens</li><li>max: 512 tokens</li></ul> |
|
| 297 |
+
* Samples:
|
| 298 |
+
| anchor | positive | negative |
|
| 299 |
+
|:----------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 300 |
+
| <code>في أي مقاطعة تقع لويسفيل أركنساس</code> | <code>لويسفيل هي بلدة في مقاطعة لافاييت ، أركنساس ، الولايات المتحدة . كان عدد السكان 1285 في تعداد عام 2000 . . المدينة هي مقر مقاطعة لافاييت .</code> | <code>ماونتن هوم ، أركنساس . ماونتن هوم هي مدينة صغيرة في مقاطعة باكستر ، أركنساس ، الولايات المتحدة ، في جبال أوزارك الجنوبية بالقرب من حدود الولاية الشمالية مع ميسوري . اعتبارا من تعداد عام 2010 ، بلغ عدد سكان المدينة 12448 نسمة .</code> |
|
| 301 |
+
| <code>متوسط سمك باب الخزانة</code> | <code>تتميز أبواب العالم القديم بميزات رائعة مثل السماكة المتزايدة ، والملامح الأعمق ، والأعمدة والقضبان الأوسع لإضفاء مظهر وإحساس أكثر دراماتيكية عند مقارنتها بأبواب الخزانة التقليدية . يبلغ عرض Stiles Rails القياسية 3 بوصات ويمكن تصنيعها في 1 و 1 1 - 8 و 1 سمك .</code> | <code>اعتمادا على الخطأ في اللوحة ، يبلغ متوسط أسعار الإصلاح 130 دولارا لإصلاح الأبواب الفولاذية و 190 دولارا للخشب و 170 دولارا للألمنيوم و 150 دولارا للألياف الزجاجية . مزيد من المعلومات حول كيفية استبدال لوحة باب المرآب . إذا تعطلت أداة فتح باب الجراج ، فقد تكون سلامتك في خطر . تريد التأكد من أن بابك يعمل بشكل صحيح حتى لا يغلق بطريق الخطأ على حيوان أليف أو شخص . تريد أيضا إغلاقها لإبعاد اللصوص عن منزلك .</code> |
|
| 302 |
+
| <code>ما هو تعريف الملء</code> | <code>اعادة تعبئه . اسم تخصيص ثان لوكيل الوصفات الطبية تم الحصول عليه من الصيدلية ، والذي يسمح به فعل الوصفة الأصلية علم الأدوية للحصول على المزيد من دواء معين ، بعد استخدام الكمية الموصوفة في البداية من الوكيل أو إعطائها . انظر الوصفة الطبية .</code> | <code>تعليمات إعادة الملء قم بإعادة الملء فقط باستخدام Spectracide ' Bug Stop Home Barrier Refill . قم بإزالة الغطاء . قم بقياس وصب 12 . 8 أونصة سائلة من المركز في حاوية فارغة سعة 1 جالون من Spectracide - Bug Stop - حاجز منزلي ، واملأه حتى 1 جالون بالماء ، استبدل الغطاء وأغلقه بإحكام . المنتج المنسكب قم بقياس 12 . 8 أونصة سائلة من المركز وصبها بحذر في حاوية فارغة سعة 1 جالون من Spectracide - حاجز منزلي من Spectracide - حاجز منزلي ، واملأه حتى 1 جالون بالماء . استبدل الغطاء وأغلقه بإحكام . امسح أي منتج مسكوب .</code> |
|
| 303 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
| 304 |
+
```json
|
| 305 |
+
{
|
| 306 |
+
"loss": "MultipleNegativesRankingLoss",
|
| 307 |
+
"matryoshka_dims": [
|
| 308 |
+
768,
|
| 309 |
+
512,
|
| 310 |
+
256,
|
| 311 |
+
128,
|
| 312 |
+
64
|
| 313 |
+
],
|
| 314 |
+
"matryoshka_weights": [
|
| 315 |
+
1,
|
| 316 |
+
1,
|
| 317 |
+
1,
|
| 318 |
+
1,
|
| 319 |
+
1
|
| 320 |
+
],
|
| 321 |
+
"n_dims_per_step": -1
|
| 322 |
+
}
|
| 323 |
+
```
|
| 324 |
+
|
| 325 |
+
### Evaluation Dataset
|
| 326 |
+
|
| 327 |
+
#### train
|
| 328 |
+
|
| 329 |
+
* Dataset: train
|
| 330 |
+
* Size: 1,129,759 evaluation samples
|
| 331 |
+
* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
|
| 332 |
+
* Approximate statistics based on the first 1000 samples:
|
| 333 |
+
| | anchor | positive | negative |
|
| 334 |
+
|:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
|
| 335 |
+
| type | string | string | string |
|
| 336 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 16.7 tokens</li><li>max: 150 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 36.54 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 35.42 tokens</li><li>max: 512 tokens</li></ul> |
|
| 337 |
+
* Samples:
|
| 338 |
+
| anchor | positive | negative |
|
| 339 |
+
|:---------------------------------------------------------------------|:---------------------------------|:----------------------------------------------------------------------|
|
| 340 |
+
| <code>رجل يرتدي سروال تنس أزرق وقميص بولو أبيض يضرب كرة التنس</code> | <code>رجل يلعب رياضة</code> | <code>هناك رجل يرتدي زي البيسبول يضرب كرة البيسبول بمضرب التنس</code> |
|
| 341 |
+
| <code>امرأة في ثوب أسود تبدو متفاجئة</code> | <code>امرأة تغيرت مشاعرها</code> | <code>امرأة تسبح في المحيط</code> |
|
| 342 |
+
| <code>رجل يرتدي قميص أبيض يقفز على شيء ما على دراجته الصفراء</code> | <code>رجل يركب دراجته</code> | <code>رجل يركب لوح التزلج فوق المنحدر</code> |
|
| 343 |
+
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
|
| 344 |
+
```json
|
| 345 |
+
{
|
| 346 |
+
"loss": "MultipleNegativesRankingLoss",
|
| 347 |
+
"matryoshka_dims": [
|
| 348 |
+
768,
|
| 349 |
+
512,
|
| 350 |
+
256,
|
| 351 |
+
128,
|
| 352 |
+
64
|
| 353 |
+
],
|
| 354 |
+
"matryoshka_weights": [
|
| 355 |
+
1,
|
| 356 |
+
1,
|
| 357 |
+
1,
|
| 358 |
+
1,
|
| 359 |
+
1
|
| 360 |
+
],
|
| 361 |
+
"n_dims_per_step": -1
|
| 362 |
+
}
|
| 363 |
+
```
|
| 364 |
+
|
| 365 |
+
### Training Hyperparameters
|
| 366 |
+
#### Non-Default Hyperparameters
|
| 367 |
+
|
| 368 |
+
- `per_device_train_batch_size`: 64
|
| 369 |
+
- `num_train_epochs`: 2
|
| 370 |
+
- `learning_rate`: 2e-05
|
| 371 |
+
- `warmup_steps`: 0.1
|
| 372 |
+
- `gradient_accumulation_steps`: 2
|
| 373 |
+
- `bf16`: True
|
| 374 |
+
- `eval_strategy`: steps
|
| 375 |
+
- `warmup_ratio`: 0.1
|
| 376 |
+
- `batch_sampler`: no_duplicates
|
| 377 |
+
|
| 378 |
+
#### All Hyperparameters
|
| 379 |
+
<details><summary>Click to expand</summary>
|
| 380 |
+
|
| 381 |
+
- `per_device_train_batch_size`: 64
|
| 382 |
+
- `num_train_epochs`: 2
|
| 383 |
+
- `max_steps`: -1
|
| 384 |
+
- `learning_rate`: 2e-05
|
| 385 |
+
- `lr_scheduler_type`: linear
|
| 386 |
+
- `lr_scheduler_kwargs`: None
|
| 387 |
+
- `warmup_steps`: 0.1
|
| 388 |
+
- `optim`: adamw_torch
|
| 389 |
+
- `optim_args`: None
|
| 390 |
+
- `weight_decay`: 0.0
|
| 391 |
+
- `adam_beta1`: 0.9
|
| 392 |
+
- `adam_beta2`: 0.999
|
| 393 |
+
- `adam_epsilon`: 1e-08
|
| 394 |
+
- `optim_target_modules`: None
|
| 395 |
+
- `gradient_accumulation_steps`: 2
|
| 396 |
+
- `average_tokens_across_devices`: True
|
| 397 |
+
- `max_grad_norm`: 1.0
|
| 398 |
+
- `label_smoothing_factor`: 0.0
|
| 399 |
+
- `bf16`: True
|
| 400 |
+
- `fp16`: False
|
| 401 |
+
- `bf16_full_eval`: False
|
| 402 |
+
- `fp16_full_eval`: False
|
| 403 |
+
- `tf32`: None
|
| 404 |
+
- `gradient_checkpointing`: False
|
| 405 |
+
- `gradient_checkpointing_kwargs`: None
|
| 406 |
+
- `torch_compile`: False
|
| 407 |
+
- `torch_compile_backend`: None
|
| 408 |
+
- `torch_compile_mode`: None
|
| 409 |
+
- `use_liger_kernel`: False
|
| 410 |
+
- `liger_kernel_config`: None
|
| 411 |
+
- `use_cache`: False
|
| 412 |
+
- `neftune_noise_alpha`: None
|
| 413 |
+
- `torch_empty_cache_steps`: None
|
| 414 |
+
- `auto_find_batch_size`: False
|
| 415 |
+
- `log_on_each_node`: True
|
| 416 |
+
- `logging_nan_inf_filter`: True
|
| 417 |
+
- `include_num_input_tokens_seen`: no
|
| 418 |
+
- `log_level`: passive
|
| 419 |
+
- `log_level_replica`: warning
|
| 420 |
+
- `disable_tqdm`: False
|
| 421 |
+
- `project`: huggingface
|
| 422 |
+
- `trackio_space_id`: trackio
|
| 423 |
+
- `eval_strategy`: steps
|
| 424 |
+
- `per_device_eval_batch_size`: 8
|
| 425 |
+
- `prediction_loss_only`: True
|
| 426 |
+
- `eval_on_start`: False
|
| 427 |
+
- `eval_do_concat_batches`: True
|
| 428 |
+
- `eval_use_gather_object`: False
|
| 429 |
+
- `eval_accumulation_steps`: None
|
| 430 |
+
- `include_for_metrics`: []
|
| 431 |
+
- `batch_eval_metrics`: False
|
| 432 |
+
- `save_only_model`: False
|
| 433 |
+
- `save_on_each_node`: False
|
| 434 |
+
- `enable_jit_checkpoint`: False
|
| 435 |
+
- `push_to_hub`: False
|
| 436 |
+
- `hub_private_repo`: None
|
| 437 |
+
- `hub_model_id`: None
|
| 438 |
+
- `hub_strategy`: every_save
|
| 439 |
+
- `hub_always_push`: False
|
| 440 |
+
- `hub_revision`: None
|
| 441 |
+
- `load_best_model_at_end`: False
|
| 442 |
+
- `ignore_data_skip`: False
|
| 443 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 444 |
+
- `full_determinism`: False
|
| 445 |
+
- `seed`: 42
|
| 446 |
+
- `data_seed`: None
|
| 447 |
+
- `use_cpu`: False
|
| 448 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 449 |
+
- `parallelism_config`: None
|
| 450 |
+
- `dataloader_drop_last`: False
|
| 451 |
+
- `dataloader_num_workers`: 0
|
| 452 |
+
- `dataloader_pin_memory`: True
|
| 453 |
+
- `dataloader_persistent_workers`: False
|
| 454 |
+
- `dataloader_prefetch_factor`: None
|
| 455 |
+
- `remove_unused_columns`: True
|
| 456 |
+
- `label_names`: None
|
| 457 |
+
- `train_sampling_strategy`: random
|
| 458 |
+
- `length_column_name`: length
|
| 459 |
+
- `ddp_find_unused_parameters`: None
|
| 460 |
+
- `ddp_bucket_cap_mb`: None
|
| 461 |
+
- `ddp_broadcast_buffers`: False
|
| 462 |
+
- `ddp_backend`: None
|
| 463 |
+
- `ddp_timeout`: 1800
|
| 464 |
+
- `fsdp`: []
|
| 465 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 466 |
+
- `deepspeed`: None
|
| 467 |
+
- `debug`: []
|
| 468 |
+
- `skip_memory_metrics`: True
|
| 469 |
+
- `do_predict`: False
|
| 470 |
+
- `resume_from_checkpoint`: None
|
| 471 |
+
- `warmup_ratio`: 0.1
|
| 472 |
+
- `local_rank`: -1
|
| 473 |
+
- `prompts`: None
|
| 474 |
+
- `batch_sampler`: no_duplicates
|
| 475 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 476 |
+
- `router_mapping`: {}
|
| 477 |
+
- `learning_rate_mapping`: {}
|
| 478 |
+
|
| 479 |
+
</details>
|
| 480 |
+
|
| 481 |
+
### Training Logs
|
| 482 |
+
<details><summary>Click to expand</summary>
|
| 483 |
+
|
| 484 |
+
| Epoch | Step | Training Loss | train loss | dev-768_cosine_accuracy | dev-512_cosine_accuracy | dev-256_cosine_accuracy | dev-128_cosine_accuracy | dev-64_cosine_accuracy |
|
| 485 |
+
|:------:|:-----:|:-------------:|:----------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|
|
| 486 |
+
| 0.5891 | 18200 | 0.8727 | - | - | - | - | - | - |
|
| 487 |
+
| 0.5956 | 18400 | 0.8524 | - | - | - | - | - | - |
|
| 488 |
+
| 0.6021 | 18600 | 0.8995 | - | - | - | - | - | - |
|
| 489 |
+
| 0.6086 | 18800 | 0.8360 | - | - | - | - | - | - |
|
| 490 |
+
| 0.6150 | 19000 | 0.8628 | - | - | - | - | - | - |
|
| 491 |
+
| 0.6215 | 19200 | 0.8244 | - | - | - | - | - | - |
|
| 492 |
+
| 0.6280 | 19400 | 0.8647 | - | - | - | - | - | - |
|
| 493 |
+
| 0.6345 | 19600 | 0.8479 | - | - | - | - | - | - |
|
| 494 |
+
| 0.6409 | 19800 | 0.8204 | - | - | - | - | - | - |
|
| 495 |
+
| 0.6474 | 20000 | 0.8359 | - | - | - | - | - | - |
|
| 496 |
+
| 0.6539 | 20200 | 0.7952 | - | - | - | - | - | - |
|
| 497 |
+
| 0.6604 | 20400 | 0.8375 | - | - | - | - | - | - |
|
| 498 |
+
| 0.6668 | 20600 | 0.8364 | - | - | - | - | - | - |
|
| 499 |
+
| 0.6733 | 20800 | 0.8131 | - | - | - | - | - | - |
|
| 500 |
+
| 0.6798 | 21000 | 0.8310 | - | - | - | - | - | - |
|
| 501 |
+
| 0.6863 | 21200 | 0.8295 | - | - | - | - | - | - |
|
| 502 |
+
| 0.6927 | 21400 | 0.7865 | - | - | - | - | - | - |
|
| 503 |
+
| 0.6992 | 21600 | 0.7960 | - | - | - | - | - | - |
|
| 504 |
+
| 0.7057 | 21800 | 0.8287 | - | - | - | - | - | - |
|
| 505 |
+
| 0.7121 | 22000 | 0.8214 | - | - | - | - | - | - |
|
| 506 |
+
| 0.7186 | 22200 | 0.7879 | - | - | - | - | - | - |
|
| 507 |
+
| 0.7251 | 22400 | 0.8139 | - | - | - | - | - | - |
|
| 508 |
+
| 0.7316 | 22600 | 0.7849 | - | - | - | - | - | - |
|
| 509 |
+
| 0.7380 | 22800 | 0.7880 | - | - | - | - | - | - |
|
| 510 |
+
| 0.7445 | 23000 | 0.7725 | - | - | - | - | - | - |
|
| 511 |
+
| 0.7510 | 23200 | 0.8086 | - | - | - | - | - | - |
|
| 512 |
+
| 0.7575 | 23400 | 0.7687 | - | - | - | - | - | - |
|
| 513 |
+
| 0.7639 | 23600 | 0.7828 | - | - | - | - | - | - |
|
| 514 |
+
| 0.7704 | 23800 | 0.7518 | - | - | - | - | - | - |
|
| 515 |
+
| 0.7769 | 24000 | 0.7599 | 0.4041 | 0.9737 | 0.9738 | 0.9738 | 0.9734 | 0.9718 |
|
| 516 |
+
| 0.7834 | 24200 | 0.7332 | - | - | - | - | - | - |
|
| 517 |
+
| 0.7898 | 24400 | 0.7476 | - | - | - | - | - | - |
|
| 518 |
+
| 0.7963 | 24600 | 0.7806 | - | - | - | - | - | - |
|
| 519 |
+
| 0.8028 | 24800 | 0.7511 | - | - | - | - | - | - |
|
| 520 |
+
| 0.8093 | 25000 | 0.7652 | - | - | - | - | - | - |
|
| 521 |
+
| 0.8157 | 25200 | 0.7883 | - | - | - | - | - | - |
|
| 522 |
+
| 0.8222 | 25400 | 0.7305 | - | - | - | - | - | - |
|
| 523 |
+
| 0.8287 | 25600 | 0.7308 | - | - | - | - | - | - |
|
| 524 |
+
| 0.8352 | 25800 | 0.7368 | - | - | - | - | - | - |
|
| 525 |
+
| 0.8416 | 26000 | 0.7432 | - | - | - | - | - | - |
|
| 526 |
+
| 0.8481 | 26200 | 0.7046 | - | - | - | - | - | - |
|
| 527 |
+
| 0.8546 | 26400 | 0.7476 | - | - | - | - | - | - |
|
| 528 |
+
| 0.8611 | 26600 | 0.7212 | - | - | - | - | - | - |
|
| 529 |
+
| 0.8675 | 26800 | 0.7335 | - | - | - | - | - | - |
|
| 530 |
+
| 0.8740 | 27000 | 0.7415 | - | - | - | - | - | - |
|
| 531 |
+
| 0.8805 | 27200 | 0.6937 | - | - | - | - | - | - |
|
| 532 |
+
| 0.8869 | 27400 | 0.7294 | - | - | - | - | - | - |
|
| 533 |
+
| 0.8934 | 27600 | 0.7436 | - | - | - | - | - | - |
|
| 534 |
+
| 0.8999 | 27800 | 0.7093 | - | - | - | - | - | - |
|
| 535 |
+
| 0.9064 | 28000 | 0.7480 | - | - | - | - | - | - |
|
| 536 |
+
| 0.9128 | 28200 | 0.7039 | - | - | - | - | - | - |
|
| 537 |
+
| 0.9193 | 28400 | 0.7091 | - | - | - | - | - | - |
|
| 538 |
+
| 0.9258 | 28600 | 0.7019 | - | - | - | - | - | - |
|
| 539 |
+
| 0.9323 | 28800 | 0.7081 | - | - | - | - | - | - |
|
| 540 |
+
| 0.9387 | 29000 | 0.6833 | - | - | - | - | - | - |
|
| 541 |
+
| 0.9452 | 29200 | 0.6982 | - | - | - | - | - | - |
|
| 542 |
+
| 0.9517 | 29400 | 0.7249 | - | - | - | - | - | - |
|
| 543 |
+
| 0.9582 | 29600 | 0.7282 | - | - | - | - | - | - |
|
| 544 |
+
| 0.9646 | 29800 | 0.7147 | - | - | - | - | - | - |
|
| 545 |
+
| 0.9711 | 30000 | 0.6742 | 0.3640 | 0.9758 | 0.9759 | 0.9761 | 0.9757 | 0.9742 |
|
| 546 |
+
| 0.9776 | 30200 | 0.6901 | - | - | - | - | - | - |
|
| 547 |
+
| 0.9841 | 30400 | 0.7067 | - | - | - | - | - | - |
|
| 548 |
+
| 0.9905 | 30600 | 0.7166 | - | - | - | - | - | - |
|
| 549 |
+
| 0.9970 | 30800 | 0.6800 | - | - | - | - | - | - |
|
| 550 |
+
| 1.0035 | 31000 | 0.6846 | - | - | - | - | - | - |
|
| 551 |
+
| 1.0099 | 31200 | 0.6723 | - | - | - | - | - | - |
|
| 552 |
+
| 1.0164 | 31400 | 0.6573 | - | - | - | - | - | - |
|
| 553 |
+
| 1.0229 | 31600 | 0.6895 | - | - | - | - | - | - |
|
| 554 |
+
| 1.0294 | 31800 | 0.6588 | - | - | - | - | - | - |
|
| 555 |
+
| 1.0358 | 32000 | 0.6517 | - | - | - | - | - | - |
|
| 556 |
+
| 1.0423 | 32200 | 0.6498 | - | - | - | - | - | - |
|
| 557 |
+
| 1.0488 | 32400 | 0.6836 | - | - | - | - | - | - |
|
| 558 |
+
| 1.0553 | 32600 | 0.6819 | - | - | - | - | - | - |
|
| 559 |
+
| 1.0617 | 32800 | 0.6463 | - | - | - | - | - | - |
|
| 560 |
+
| 1.0682 | 33000 | 0.6645 | - | - | - | - | - | - |
|
| 561 |
+
| 1.0747 | 33200 | 0.6518 | - | - | - | - | - | - |
|
| 562 |
+
| 1.0812 | 33400 | 0.6235 | - | - | - | - | - | - |
|
| 563 |
+
| 1.0876 | 33600 | 0.6302 | - | - | - | - | - | - |
|
| 564 |
+
| 1.0941 | 33800 | 0.6452 | - | - | - | - | - | - |
|
| 565 |
+
| 1.1006 | 34000 | 0.6477 | - | - | - | - | - | - |
|
| 566 |
+
| 1.1070 | 34200 | 0.6084 | - | - | - | - | - | - |
|
| 567 |
+
| 1.1135 | 34400 | 0.6259 | - | - | - | - | - | - |
|
| 568 |
+
| 1.1200 | 34600 | 0.6070 | - | - | - | - | - | - |
|
| 569 |
+
| 1.1265 | 34800 | 0.5977 | - | - | - | - | - | - |
|
| 570 |
+
| 1.1329 | 35000 | 0.6044 | - | - | - | - | - | - |
|
| 571 |
+
| 1.1394 | 35200 | 0.6007 | - | - | - | - | - | - |
|
| 572 |
+
| 1.1459 | 35400 | 0.5628 | - | - | - | - | - | - |
|
| 573 |
+
| 1.1524 | 35600 | 0.5732 | - | - | - | - | - | - |
|
| 574 |
+
| 1.1588 | 35800 | 0.5773 | - | - | - | - | - | - |
|
| 575 |
+
| 1.1653 | 36000 | 0.5719 | 0.3356 | 0.9775 | 0.9777 | 0.9777 | 0.9774 | 0.9760 |
|
| 576 |
+
| 1.1718 | 36200 | 0.5471 | - | - | - | - | - | - |
|
| 577 |
+
| 1.1783 | 36400 | 0.5635 | - | - | - | - | - | - |
|
| 578 |
+
| 1.1847 | 36600 | 0.5390 | - | - | - | - | - | - |
|
| 579 |
+
| 1.1912 | 36800 | 0.5428 | - | - | - | - | - | - |
|
| 580 |
+
| 1.1977 | 37000 | 0.5205 | - | - | - | - | - | - |
|
| 581 |
+
| 1.2042 | 37200 | 0.5362 | - | - | - | - | - | - |
|
| 582 |
+
| 1.2106 | 37400 | 0.5386 | - | - | - | - | - | - |
|
| 583 |
+
| 1.2171 | 37600 | 0.5203 | - | - | - | - | - | - |
|
| 584 |
+
| 1.2236 | 37800 | 0.5301 | - | - | - | - | - | - |
|
| 585 |
+
| 1.2301 | 38000 | 0.5232 | - | - | - | - | - | - |
|
| 586 |
+
| 1.2365 | 38200 | 0.4922 | - | - | - | - | - | - |
|
| 587 |
+
| 1.2430 | 38400 | 0.5029 | - | - | - | - | - | - |
|
| 588 |
+
| 1.2495 | 38600 | 0.4989 | - | - | - | - | - | - |
|
| 589 |
+
| 1.2560 | 38800 | 0.5053 | - | - | - | - | - | - |
|
| 590 |
+
| 1.2624 | 39000 | 0.5081 | - | - | - | - | - | - |
|
| 591 |
+
| 1.2689 | 39200 | 0.4960 | - | - | - | - | - | - |
|
| 592 |
+
| 1.2754 | 39400 | 0.5052 | - | - | - | - | - | - |
|
| 593 |
+
| 1.2818 | 39600 | 0.4984 | - | - | - | - | - | - |
|
| 594 |
+
| 1.2883 | 39800 | 0.4909 | - | - | - | - | - | - |
|
| 595 |
+
| 1.2948 | 40000 | 0.5120 | - | - | - | - | - | - |
|
| 596 |
+
| 1.3013 | 40200 | 0.4873 | - | - | - | - | - | - |
|
| 597 |
+
| 1.3077 | 40400 | 0.4896 | - | - | - | - | - | - |
|
| 598 |
+
| 1.3142 | 40600 | 0.4900 | - | - | - | - | - | - |
|
| 599 |
+
| 1.3207 | 40800 | 0.5036 | - | - | - | - | - | - |
|
| 600 |
+
| 1.3272 | 41000 | 0.4876 | - | - | - | - | - | - |
|
| 601 |
+
| 1.3336 | 41200 | 0.4705 | - | - | - | - | - | - |
|
| 602 |
+
| 1.3401 | 41400 | 0.4786 | - | - | - | - | - | - |
|
| 603 |
+
| 1.3466 | 41600 | 0.4998 | - | - | - | - | - | - |
|
| 604 |
+
| 1.3531 | 41800 | 0.4692 | - | - | - | - | - | - |
|
| 605 |
+
| 1.3595 | 42000 | 0.5064 | 0.3160 | 0.9788 | 0.9790 | 0.9790 | 0.9785 | 0.9774 |
|
| 606 |
+
| 1.3660 | 42200 | 0.4925 | - | - | - | - | - | - |
|
| 607 |
+
| 1.3725 | 42400 | 0.4601 | - | - | - | - | - | - |
|
| 608 |
+
| 1.3790 | 42600 | 0.4762 | - | - | - | - | - | - |
|
| 609 |
+
| 1.3854 | 42800 | 0.4986 | - | - | - | - | - | - |
|
| 610 |
+
| 1.3919 | 43000 | 0.4656 | - | - | - | - | - | - |
|
| 611 |
+
| 1.3984 | 43200 | 0.4507 | - | - | - | - | - | - |
|
| 612 |
+
| 1.4049 | 43400 | 0.4862 | - | - | - | - | - | - |
|
| 613 |
+
| 1.4113 | 43600 | 0.4596 | - | - | - | - | - | - |
|
| 614 |
+
| 1.4178 | 43800 | 0.4696 | - | - | - | - | - | - |
|
| 615 |
+
| 1.4243 | 44000 | 0.4925 | - | - | - | - | - | - |
|
| 616 |
+
| 1.4308 | 44200 | 0.4796 | - | - | - | - | - | - |
|
| 617 |
+
| 1.4372 | 44400 | 0.4525 | - | - | - | - | - | - |
|
| 618 |
+
| 1.4437 | 44600 | 0.4717 | - | - | - | - | - | - |
|
| 619 |
+
| 1.4502 | 44800 | 0.4803 | - | - | - | - | - | - |
|
| 620 |
+
| 1.4566 | 45000 | 0.4675 | - | - | - | - | - | - |
|
| 621 |
+
| 1.4631 | 45200 | 0.4631 | - | - | - | - | - | - |
|
| 622 |
+
| 1.4696 | 45400 | 0.4622 | - | - | - | - | - | - |
|
| 623 |
+
| 1.4761 | 45600 | 0.4496 | - | - | - | - | - | - |
|
| 624 |
+
| 1.4825 | 45800 | 0.4678 | - | - | - | - | - | - |
|
| 625 |
+
| 1.4890 | 46000 | 0.4495 | - | - | - | - | - | - |
|
| 626 |
+
| 1.4955 | 46200 | 0.4474 | - | - | - | - | - | - |
|
| 627 |
+
| 1.5020 | 46400 | 0.4587 | - | - | - | - | - | - |
|
| 628 |
+
| 1.5084 | 46600 | 0.4591 | - | - | - | - | - | - |
|
| 629 |
+
| 1.5149 | 46800 | 0.4573 | - | - | - | - | - | - |
|
| 630 |
+
| 1.5214 | 47000 | 0.4442 | - | - | - | - | - | - |
|
| 631 |
+
| 1.5279 | 47200 | 0.4550 | - | - | - | - | - | - |
|
| 632 |
+
| 1.5343 | 47400 | 0.4493 | - | - | - | - | - | - |
|
| 633 |
+
| 1.5408 | 47600 | 0.4485 | - | - | - | - | - | - |
|
| 634 |
+
| 1.5473 | 47800 | 0.4569 | - | - | - | - | - | - |
|
| 635 |
+
| 1.5538 | 48000 | 0.4346 | 0.3001 | 0.9799 | 0.9802 | 0.9802 | 0.9798 | 0.9788 |
|
| 636 |
+
| 1.5602 | 48200 | 0.4469 | - | - | - | - | - | - |
|
| 637 |
+
| 1.5667 | 48400 | 0.4602 | - | - | - | - | - | - |
|
| 638 |
+
| 1.5732 | 48600 | 0.4430 | - | - | - | - | - | - |
|
| 639 |
+
| 1.5797 | 48800 | 0.4524 | - | - | - | - | - | - |
|
| 640 |
+
| 1.5861 | 49000 | 0.4528 | - | - | - | - | - | - |
|
| 641 |
+
| 1.5926 | 49200 | 0.4348 | - | - | - | - | - | - |
|
| 642 |
+
| 1.5991 | 49400 | 0.4533 | - | - | - | - | - | - |
|
| 643 |
+
| 1.6056 | 49600 | 0.4523 | - | - | - | - | - | - |
|
| 644 |
+
| 1.6120 | 49800 | 0.4509 | - | - | - | - | - | - |
|
| 645 |
+
| 1.6185 | 50000 | 0.4365 | - | - | - | - | - | - |
|
| 646 |
+
| 1.6250 | 50200 | 0.4504 | - | - | - | - | - | - |
|
| 647 |
+
| 1.6314 | 50400 | 0.4292 | - | - | - | - | - | - |
|
| 648 |
+
| 1.6379 | 50600 | 0.4406 | - | - | - | - | - | - |
|
| 649 |
+
| 1.6444 | 50800 | 0.4333 | - | - | - | - | - | - |
|
| 650 |
+
| 1.6509 | 51000 | 0.4361 | - | - | - | - | - | - |
|
| 651 |
+
| 1.6573 | 51200 | 0.4065 | - | - | - | - | - | - |
|
| 652 |
+
| 1.6638 | 51400 | 0.4671 | - | - | - | - | - | - |
|
| 653 |
+
| 1.6703 | 51600 | 0.4328 | - | - | - | - | - | - |
|
| 654 |
+
| 1.6768 | 51800 | 0.4310 | - | - | - | - | - | - |
|
| 655 |
+
| 1.6832 | 52000 | 0.4523 | - | - | - | - | - | - |
|
| 656 |
+
| 1.6897 | 52200 | 0.4232 | - | - | - | - | - | - |
|
| 657 |
+
| 1.6962 | 52400 | 0.4257 | - | - | - | - | - | - |
|
| 658 |
+
| 1.7027 | 52600 | 0.4448 | - | - | - | - | - | - |
|
| 659 |
+
| 1.7091 | 52800 | 0.4491 | - | - | - | - | - | - |
|
| 660 |
+
| 1.7156 | 53000 | 0.4224 | - | - | - | - | - | - |
|
| 661 |
+
| 1.7221 | 53200 | 0.4297 | - | - | - | - | - | - |
|
| 662 |
+
| 1.7286 | 53400 | 0.4522 | - | - | - | - | - | - |
|
| 663 |
+
| 1.7350 | 53600 | 0.4195 | - | - | - | - | - | - |
|
| 664 |
+
| 1.7415 | 53800 | 0.4227 | - | - | - | - | - | - |
|
| 665 |
+
| 1.7480 | 54000 | 0.4381 | 0.2875 | 0.9807 | 0.9808 | 0.9808 | 0.9805 | 0.9794 |
|
| 666 |
+
| 1.7545 | 54200 | 0.4460 | - | - | - | - | - | - |
|
| 667 |
+
| 1.7609 | 54400 | 0.4260 | - | - | - | - | - | - |
|
| 668 |
+
| 1.7674 | 54600 | 0.4299 | - | - | - | - | - | - |
|
| 669 |
+
| 1.7739 | 54800 | 0.4247 | - | - | - | - | - | - |
|
| 670 |
+
| 1.7804 | 55000 | 0.4244 | - | - | - | - | - | - |
|
| 671 |
+
| 1.7868 | 55200 | 0.4185 | - | - | - | - | - | - |
|
| 672 |
+
| 1.7933 | 55400 | 0.4292 | - | - | - | - | - | - |
|
| 673 |
+
| 1.7998 | 55600 | 0.4468 | - | - | - | - | - | - |
|
| 674 |
+
| 1.8062 | 55800 | 0.4118 | - | - | - | - | - | - |
|
| 675 |
+
| 1.8127 | 56000 | 0.4306 | - | - | - | - | - | - |
|
| 676 |
+
| 1.8192 | 56200 | 0.4447 | - | - | - | - | - | - |
|
| 677 |
+
| 1.8257 | 56400 | 0.4147 | - | - | - | - | - | - |
|
| 678 |
+
| 1.8321 | 56600 | 0.4189 | - | - | - | - | - | - |
|
| 679 |
+
| 1.8386 | 56800 | 0.4167 | - | - | - | - | - | - |
|
| 680 |
+
| 1.8451 | 57000 | 0.4022 | - | - | - | - | - | - |
|
| 681 |
+
| 1.8516 | 57200 | 0.4158 | - | - | - | - | - | - |
|
| 682 |
+
| 1.8580 | 57400 | 0.4228 | - | - | - | - | - | - |
|
| 683 |
+
| 1.8645 | 57600 | 0.4256 | - | - | - | - | - | - |
|
| 684 |
+
| 1.8710 | 57800 | 0.4251 | - | - | - | - | - | - |
|
| 685 |
+
| 1.8775 | 58000 | 0.4232 | - | - | - | - | - | - |
|
| 686 |
+
| 1.8839 | 58200 | 0.4143 | - | - | - | - | - | - |
|
| 687 |
+
| 1.8904 | 58400 | 0.4331 | - | - | - | - | - | - |
|
| 688 |
+
| 1.8969 | 58600 | 0.4253 | - | - | - | - | - | - |
|
| 689 |
+
| 1.9034 | 58800 | 0.4410 | - | - | - | - | - | - |
|
| 690 |
+
| 1.9098 | 59000 | 0.4337 | - | - | - | - | - | - |
|
| 691 |
+
| 1.9163 | 59200 | 0.4016 | - | - | - | - | - | - |
|
| 692 |
+
| 1.9228 | 59400 | 0.4249 | - | - | - | - | - | - |
|
| 693 |
+
| 1.9293 | 59600 | 0.4108 | - | - | - | - | - | - |
|
| 694 |
+
| 1.9357 | 59800 | 0.4272 | - | - | - | - | - | - |
|
| 695 |
+
| 1.9422 | 60000 | 0.3916 | 0.2812 | 0.9810 | 0.9811 | 0.9813 | 0.9811 | 0.9797 |
|
| 696 |
+
| 1.9487 | 60200 | 0.4334 | - | - | - | - | - | - |
|
| 697 |
+
| 1.9552 | 60400 | 0.4462 | - | - | - | - | - | - |
|
| 698 |
+
| 1.9616 | 60600 | 0.4436 | - | - | - | - | - | - |
|
| 699 |
+
| 1.9681 | 60800 | 0.4278 | - | - | - | - | - | - |
|
| 700 |
+
| 1.9746 | 61000 | 0.4170 | - | - | - | - | - | - |
|
| 701 |
+
| 1.9810 | 61200 | 0.4376 | - | - | - | - | - | - |
|
| 702 |
+
| 1.9875 | 61400 | 0.4433 | - | - | - | - | - | - |
|
| 703 |
+
| 1.9940 | 61600 | 0.4292 | - | - | - | - | - | - |
|
| 704 |
+
|
| 705 |
+
</details>
|
| 706 |
+
|
| 707 |
+
### Framework Versions
|
| 708 |
+
- Python: 3.10.19
|
| 709 |
+
- Sentence Transformers: 5.2.3
|
| 710 |
+
- Transformers: 5.2.0
|
| 711 |
+
- PyTorch: 2.6.0+cu124
|
| 712 |
+
- Accelerate: 1.12.0
|
| 713 |
+
- Datasets: 4.5.0
|
| 714 |
+
- Tokenizers: 0.22.2
|
| 715 |
+
|
| 716 |
+
## Citation
|
| 717 |
+
|
| 718 |
+
### BibTeX
|
| 719 |
+
|
| 720 |
+
#### Sentence Transformers
|
| 721 |
+
```bibtex
|
| 722 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 723 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 724 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 725 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 726 |
+
month = "11",
|
| 727 |
+
year = "2019",
|
| 728 |
+
publisher = "Association for Computational Linguistics",
|
| 729 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 730 |
+
}
|
| 731 |
+
```
|
| 732 |
+
|
| 733 |
+
#### MatryoshkaLoss
|
| 734 |
+
```bibtex
|
| 735 |
+
@misc{kusupati2024matryoshka,
|
| 736 |
+
title={Matryoshka Representation Learning},
|
| 737 |
+
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
|
| 738 |
+
year={2024},
|
| 739 |
+
eprint={2205.13147},
|
| 740 |
+
archivePrefix={arXiv},
|
| 741 |
+
primaryClass={cs.LG}
|
| 742 |
+
}
|
| 743 |
+
```
|
| 744 |
+
|
| 745 |
+
#### MultipleNegativesRankingLoss
|
| 746 |
+
```bibtex
|
| 747 |
+
@misc{henderson2017efficient,
|
| 748 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
| 749 |
+
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
| 750 |
+
year={2017},
|
| 751 |
+
eprint={1705.00652},
|
| 752 |
+
archivePrefix={arXiv},
|
| 753 |
+
primaryClass={cs.CL}
|
| 754 |
+
}
|
| 755 |
+
```
|
| 756 |
+
|
| 757 |
+
<!--
|
| 758 |
+
## Glossary
|
| 759 |
+
|
| 760 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 761 |
+
-->
|
| 762 |
+
|
| 763 |
+
<!--
|
| 764 |
+
## Model Card Authors
|
| 765 |
+
|
| 766 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 767 |
+
-->
|
| 768 |
+
|
| 769 |
+
<!--
|
| 770 |
+
## Model Card Contact
|
| 771 |
+
|
| 772 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 773 |
+
-->
|
epoch2/model/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"max_position_embeddings": 512,
|
| 19 |
+
"model_type": "bert",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"transformers_version": "5.2.0",
|
| 25 |
+
"type_vocab_size": 2,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 64000
|
| 28 |
+
}
|
epoch2/model/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "SentenceTransformer",
|
| 3 |
+
"__version__": {
|
| 4 |
+
"sentence_transformers": "5.2.3",
|
| 5 |
+
"transformers": "5.2.0",
|
| 6 |
+
"pytorch": "2.6.0+cu124"
|
| 7 |
+
},
|
| 8 |
+
"prompts": {
|
| 9 |
+
"query": "",
|
| 10 |
+
"document": ""
|
| 11 |
+
},
|
| 12 |
+
"default_prompt_name": null,
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
epoch2/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:602c1647dc30e982f7f4b007ac82f3a97ef88b815b598d41e6c8d075be10730f
|
| 3 |
+
size 540795728
|
epoch2/model/modules.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
}
|
| 14 |
+
]
|
epoch2/model/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
epoch2/model/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
epoch2/model/tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"max_len": 512,
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"never_split": [
|
| 11 |
+
"[بريد]",
|
| 12 |
+
"[مستخدم]",
|
| 13 |
+
"[رابط]"
|
| 14 |
+
],
|
| 15 |
+
"pad_token": "[PAD]",
|
| 16 |
+
"sep_token": "[SEP]",
|
| 17 |
+
"strip_accents": null,
|
| 18 |
+
"tokenize_chinese_chars": true,
|
| 19 |
+
"tokenizer_class": "BertTokenizer",
|
| 20 |
+
"unk_token": "[UNK]"
|
| 21 |
+
}
|
epoch2/output.log
ADDED
|
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
--- RESUMING FROM: /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-18000 ---
|
| 2 |
+
{'loss': '0.8727', 'grad_norm': '5.438', 'learning_rate': '1.568e-05', 'epoch': '0.5891'}
|
| 3 |
+
{'loss': '0.8524', 'grad_norm': '5.458', 'learning_rate': '1.56e-05', 'epoch': '0.5956'}
|
| 4 |
+
{'loss': '0.8995', 'grad_norm': '6.666', 'learning_rate': '1.553e-05', 'epoch': '0.6021'}
|
| 5 |
+
{'loss': '0.836', 'grad_norm': '5.681', 'learning_rate': '1.546e-05', 'epoch': '0.6086'}
|
| 6 |
+
{'loss': '0.8628', 'grad_norm': '6.571', 'learning_rate': '1.539e-05', 'epoch': '0.615'}
|
| 7 |
+
{'loss': '0.8244', 'grad_norm': '6.389', 'learning_rate': '1.532e-05', 'epoch': '0.6215'}
|
| 8 |
+
{'loss': '0.8647', 'grad_norm': '4.987', 'learning_rate': '1.525e-05', 'epoch': '0.628'}
|
| 9 |
+
{'loss': '0.8479', 'grad_norm': '4.451', 'learning_rate': '1.517e-05', 'epoch': '0.6345'}
|
| 10 |
+
{'loss': '0.8204', 'grad_norm': '5.356', 'learning_rate': '1.51e-05', 'epoch': '0.6409'}
|
| 11 |
+
{'loss': '0.8359', 'grad_norm': '5.146', 'learning_rate': '1.503e-05', 'epoch': '0.6474'}
|
| 12 |
+
{'loss': '0.7952', 'grad_norm': '4.308', 'learning_rate': '1.496e-05', 'epoch': '0.6539'}
|
| 13 |
+
{'loss': '0.8375', 'grad_norm': '5.216', 'learning_rate': '1.489e-05', 'epoch': '0.6604'}
|
| 14 |
+
{'loss': '0.8364', 'grad_norm': '5.812', 'learning_rate': '1.481e-05', 'epoch': '0.6668'}
|
| 15 |
+
{'loss': '0.8131', 'grad_norm': '5.52', 'learning_rate': '1.474e-05', 'epoch': '0.6733'}
|
| 16 |
+
{'loss': '0.831', 'grad_norm': '6.452', 'learning_rate': '1.467e-05', 'epoch': '0.6798'}
|
| 17 |
+
{'loss': '0.8295', 'grad_norm': '4.274', 'learning_rate': '1.46e-05', 'epoch': '0.6863'}
|
| 18 |
+
{'loss': '0.7865', 'grad_norm': '4.77', 'learning_rate': '1.453e-05', 'epoch': '0.6927'}
|
| 19 |
+
{'loss': '0.796', 'grad_norm': '5.027', 'learning_rate': '1.445e-05', 'epoch': '0.6992'}
|
| 20 |
+
{'loss': '0.8287', 'grad_norm': '4.826', 'learning_rate': '1.438e-05', 'epoch': '0.7057'}
|
| 21 |
+
{'loss': '0.8214', 'grad_norm': '4.381', 'learning_rate': '1.431e-05', 'epoch': '0.7121'}
|
| 22 |
+
{'loss': '0.7879', 'grad_norm': '6.475', 'learning_rate': '1.424e-05', 'epoch': '0.7186'}
|
| 23 |
+
{'loss': '0.8139', 'grad_norm': '5.295', 'learning_rate': '1.417e-05', 'epoch': '0.7251'}
|
| 24 |
+
{'loss': '0.7849', 'grad_norm': '5.051', 'learning_rate': '1.409e-05', 'epoch': '0.7316'}
|
| 25 |
+
{'loss': '0.788', 'grad_norm': '5.113', 'learning_rate': '1.402e-05', 'epoch': '0.738'}
|
| 26 |
+
{'loss': '0.7725', 'grad_norm': '4.049', 'learning_rate': '1.395e-05', 'epoch': '0.7445'}
|
| 27 |
+
{'loss': '0.8086', 'grad_norm': '4.646', 'learning_rate': '1.388e-05', 'epoch': '0.751'}
|
| 28 |
+
{'loss': '0.7687', 'grad_norm': '5.049', 'learning_rate': '1.381e-05', 'epoch': '0.7575'}
|
| 29 |
+
{'loss': '0.7828', 'grad_norm': '6.568', 'learning_rate': '1.373e-05', 'epoch': '0.7639'}
|
| 30 |
+
{'loss': '0.7518', 'grad_norm': '5.9', 'learning_rate': '1.366e-05', 'epoch': '0.7704'}
|
| 31 |
+
{'loss': '0.7599', 'grad_norm': '6.338', 'learning_rate': '1.359e-05', 'epoch': '0.7769'}
|
| 32 |
+
{'eval_train_loss': '0.4041', 'eval_dev-768_cosine_accuracy': '0.9737', 'eval_dev-512_cosine_accuracy': '0.9738', 'eval_dev-256_cosine_accuracy': '0.9738', 'eval_dev-128_cosine_accuracy': '0.9734', 'eval_dev-64_cosine_accuracy': '0.9718', 'eval_sequential_score': '0.9737', 'eval_train_runtime': '9673', 'eval_train_samples_per_second': '116.8', 'eval_train_steps_per_second': '14.6', 'epoch': '0.7769'}
|
| 33 |
+
{'loss': '0.7332', 'grad_norm': '4.95', 'learning_rate': '1.352e-05', 'epoch': '0.7834'}
|
| 34 |
+
{'loss': '0.7476', 'grad_norm': '4.513', 'learning_rate': '1.345e-05', 'epoch': '0.7898'}
|
| 35 |
+
{'loss': '0.7806', 'grad_norm': '5.095', 'learning_rate': '1.337e-05', 'epoch': '0.7963'}
|
| 36 |
+
{'loss': '0.7511', 'grad_norm': '5.826', 'learning_rate': '1.33e-05', 'epoch': '0.8028'}
|
| 37 |
+
{'loss': '0.7652', 'grad_norm': '6.09', 'learning_rate': '1.323e-05', 'epoch': '0.8093'}
|
| 38 |
+
{'loss': '0.7883', 'grad_norm': '4.332', 'learning_rate': '1.316e-05', 'epoch': '0.8157'}
|
| 39 |
+
{'loss': '0.7305', 'grad_norm': '5.749', 'learning_rate': '1.309e-05', 'epoch': '0.8222'}
|
| 40 |
+
{'loss': '0.7308', 'grad_norm': '4.871', 'learning_rate': '1.302e-05', 'epoch': '0.8287'}
|
| 41 |
+
{'loss': '0.7368', 'grad_norm': '4.618', 'learning_rate': '1.294e-05', 'epoch': '0.8352'}
|
| 42 |
+
{'loss': '0.7432', 'grad_norm': '4.836', 'learning_rate': '1.287e-05', 'epoch': '0.8416'}
|
| 43 |
+
{'loss': '0.7046', 'grad_norm': '4.988', 'learning_rate': '1.28e-05', 'epoch': '0.8481'}
|
| 44 |
+
{'loss': '0.7476', 'grad_norm': '4.596', 'learning_rate': '1.273e-05', 'epoch': '0.8546'}
|
| 45 |
+
{'loss': '0.7212', 'grad_norm': '5.712', 'learning_rate': '1.266e-05', 'epoch': '0.8611'}
|
| 46 |
+
{'loss': '0.7335', 'grad_norm': '3.99', 'learning_rate': '1.258e-05', 'epoch': '0.8675'}
|
| 47 |
+
{'loss': '0.7415', 'grad_norm': '5.446', 'learning_rate': '1.251e-05', 'epoch': '0.874'}
|
| 48 |
+
{'loss': '0.6937', 'grad_norm': '5.257', 'learning_rate': '1.244e-05', 'epoch': '0.8805'}
|
| 49 |
+
{'loss': '0.7294', 'grad_norm': '5.302', 'learning_rate': '1.237e-05', 'epoch': '0.8869'}
|
| 50 |
+
{'loss': '0.7436', 'grad_norm': '3.847', 'learning_rate': '1.23e-05', 'epoch': '0.8934'}
|
| 51 |
+
{'loss': '0.7093', 'grad_norm': '6.182', 'learning_rate': '1.222e-05', 'epoch': '0.8999'}
|
| 52 |
+
{'loss': '0.748', 'grad_norm': '5.445', 'learning_rate': '1.215e-05', 'epoch': '0.9064'}
|
| 53 |
+
{'loss': '0.7039', 'grad_norm': '5.002', 'learning_rate': '1.208e-05', 'epoch': '0.9128'}
|
| 54 |
+
{'loss': '0.7091', 'grad_norm': '5.085', 'learning_rate': '1.201e-05', 'epoch': '0.9193'}
|
| 55 |
+
{'loss': '0.7019', 'grad_norm': '5.379', 'learning_rate': '1.194e-05', 'epoch': '0.9258'}
|
| 56 |
+
{'loss': '0.7081', 'grad_norm': '5.63', 'learning_rate': '1.186e-05', 'epoch': '0.9323'}
|
| 57 |
+
{'loss': '0.6833', 'grad_norm': '2.541', 'learning_rate': '1.179e-05', 'epoch': '0.9387'}
|
| 58 |
+
{'loss': '0.6982', 'grad_norm': '5.714', 'learning_rate': '1.172e-05', 'epoch': '0.9452'}
|
| 59 |
+
{'loss': '0.7249', 'grad_norm': '5.051', 'learning_rate': '1.165e-05', 'epoch': '0.9517'}
|
| 60 |
+
{'loss': '0.7282', 'grad_norm': '6.322', 'learning_rate': '1.158e-05', 'epoch': '0.9582'}
|
| 61 |
+
{'loss': '0.7147', 'grad_norm': '4.961', 'learning_rate': '1.15e-05', 'epoch': '0.9646'}
|
| 62 |
+
{'loss': '0.6742', 'grad_norm': '4.871', 'learning_rate': '1.143e-05', 'epoch': '0.9711'}
|
| 63 |
+
{'eval_train_loss': '0.364', 'eval_dev-768_cosine_accuracy': '0.9758', 'eval_dev-512_cosine_accuracy': '0.9759', 'eval_dev-256_cosine_accuracy': '0.9761', 'eval_dev-128_cosine_accuracy': '0.9757', 'eval_dev-64_cosine_accuracy': '0.9742', 'eval_sequential_score': '0.9758', 'eval_train_runtime': '9649', 'eval_train_samples_per_second': '117.1', 'eval_train_steps_per_second': '14.64', 'epoch': '0.9711'}
|
| 64 |
+
{'loss': '0.6901', 'grad_norm': '3.348', 'learning_rate': '1.136e-05', 'epoch': '0.9776'}
|
| 65 |
+
{'loss': '0.7067', 'grad_norm': '3.76', 'learning_rate': '1.129e-05', 'epoch': '0.9841'}
|
| 66 |
+
{'loss': '0.7166', 'grad_norm': '4.729', 'learning_rate': '1.122e-05', 'epoch': '0.9905'}
|
| 67 |
+
{'loss': '0.68', 'grad_norm': '4.648', 'learning_rate': '1.114e-05', 'epoch': '0.997'}
|
| 68 |
+
{'loss': '0.6846', 'grad_norm': '4.427', 'learning_rate': '1.107e-05', 'epoch': '1.003'}
|
| 69 |
+
{'loss': '0.6723', 'grad_norm': '4.459', 'learning_rate': '1.1e-05', 'epoch': '1.01'}
|
| 70 |
+
{'loss': '0.6573', 'grad_norm': '6.387', 'learning_rate': '1.093e-05', 'epoch': '1.016'}
|
| 71 |
+
{'loss': '0.6895', 'grad_norm': '4.1', 'learning_rate': '1.086e-05', 'epoch': '1.023'}
|
| 72 |
+
{'loss': '0.6588', 'grad_norm': '5.927', 'learning_rate': '1.079e-05', 'epoch': '1.029'}
|
| 73 |
+
{'loss': '0.6517', 'grad_norm': '5.9', 'learning_rate': '1.071e-05', 'epoch': '1.036'}
|
| 74 |
+
{'loss': '0.6498', 'grad_norm': '4.736', 'learning_rate': '1.064e-05', 'epoch': '1.042'}
|
| 75 |
+
{'loss': '0.6836', 'grad_norm': '5.029', 'learning_rate': '1.057e-05', 'epoch': '1.049'}
|
| 76 |
+
{'loss': '0.6819', 'grad_norm': '2.595', 'learning_rate': '1.05e-05', 'epoch': '1.055'}
|
| 77 |
+
{'loss': '0.6463', 'grad_norm': '4.963', 'learning_rate': '1.043e-05', 'epoch': '1.062'}
|
| 78 |
+
{'loss': '0.6645', 'grad_norm': '5.046', 'learning_rate': '1.035e-05', 'epoch': '1.068'}
|
| 79 |
+
{'loss': '0.6518', 'grad_norm': '3.307', 'learning_rate': '1.028e-05', 'epoch': '1.075'}
|
| 80 |
+
{'loss': '0.6235', 'grad_norm': '3.848', 'learning_rate': '1.021e-05', 'epoch': '1.081'}
|
| 81 |
+
{'loss': '0.6302', 'grad_norm': '4.664', 'learning_rate': '1.014e-05', 'epoch': '1.088'}
|
| 82 |
+
{'loss': '0.6452', 'grad_norm': '5.47', 'learning_rate': '1.007e-05', 'epoch': '1.094'}
|
| 83 |
+
{'loss': '0.6477', 'grad_norm': '5.26', 'learning_rate': '9.994e-06', 'epoch': '1.101'}
|
| 84 |
+
{'loss': '0.6084', 'grad_norm': '4.313', 'learning_rate': '9.922e-06', 'epoch': '1.107'}
|
| 85 |
+
{'loss': '0.6259', 'grad_norm': '6.499', 'learning_rate': '9.85e-06', 'epoch': '1.114'}
|
| 86 |
+
{'loss': '0.607', 'grad_norm': '3.922', 'learning_rate': '9.778e-06', 'epoch': '1.12'}
|
| 87 |
+
{'loss': '0.5977', 'grad_norm': '5.37', 'learning_rate': '9.706e-06', 'epoch': '1.126'}
|
| 88 |
+
{'loss': '0.6044', 'grad_norm': '5.068', 'learning_rate': '9.634e-06', 'epoch': '1.133'}
|
| 89 |
+
{'loss': '0.6007', 'grad_norm': '4.109', 'learning_rate': '9.562e-06', 'epoch': '1.139'}
|
| 90 |
+
{'loss': '0.5628', 'grad_norm': '4.954', 'learning_rate': '9.491e-06', 'epoch': '1.146'}
|
| 91 |
+
{'loss': '0.5732', 'grad_norm': '4.068', 'learning_rate': '9.419e-06', 'epoch': '1.152'}
|
| 92 |
+
{'loss': '0.5773', 'grad_norm': '4.939', 'learning_rate': '9.347e-06', 'epoch': '1.159'}
|
| 93 |
+
{'loss': '0.5719', 'grad_norm': '4.418', 'learning_rate': '9.275e-06', 'epoch': '1.165'}
|
| 94 |
+
{'eval_train_loss': '0.3356', 'eval_dev-768_cosine_accuracy': '0.9775', 'eval_dev-512_cosine_accuracy': '0.9777', 'eval_dev-256_cosine_accuracy': '0.9777', 'eval_dev-128_cosine_accuracy': '0.9774', 'eval_dev-64_cosine_accuracy': '0.976', 'eval_sequential_score': '0.9775', 'eval_train_runtime': '1.01e+04', 'eval_train_samples_per_second': '111.8', 'eval_train_steps_per_second': '13.98', 'epoch': '1.165'}
|
| 95 |
+
{'loss': '0.5471', 'grad_norm': '3.58', 'learning_rate': '9.203e-06', 'epoch': '1.172'}
|
| 96 |
+
{'loss': '0.5635', 'grad_norm': '5.198', 'learning_rate': '9.131e-06', 'epoch': '1.178'}
|
| 97 |
+
{'loss': '0.539', 'grad_norm': '4.468', 'learning_rate': '9.059e-06', 'epoch': '1.185'}
|
| 98 |
+
{'loss': '0.5428', 'grad_norm': '4.349', 'learning_rate': '8.987e-06', 'epoch': '1.191'}
|
| 99 |
+
{'loss': '0.5205', 'grad_norm': '2.936', 'learning_rate': '8.915e-06', 'epoch': '1.198'}
|
| 100 |
+
{'loss': '0.5362', 'grad_norm': '3.337', 'learning_rate': '8.843e-06', 'epoch': '1.204'}
|
| 101 |
+
{'loss': '0.5386', 'grad_norm': '5.76', 'learning_rate': '8.771e-06', 'epoch': '1.211'}
|
| 102 |
+
{'loss': '0.5203', 'grad_norm': '3.261', 'learning_rate': '8.699e-06', 'epoch': '1.217'}
|
| 103 |
+
{'loss': '0.5301', 'grad_norm': '3.732', 'learning_rate': '8.627e-06', 'epoch': '1.224'}
|
| 104 |
+
{'loss': '0.5232', 'grad_norm': '4.54', 'learning_rate': '8.555e-06', 'epoch': '1.23'}
|
| 105 |
+
{'loss': '0.4922', 'grad_norm': '4.291', 'learning_rate': '8.483e-06', 'epoch': '1.237'}
|
| 106 |
+
{'loss': '0.5029', 'grad_norm': '3.979', 'learning_rate': '8.412e-06', 'epoch': '1.243'}
|
| 107 |
+
{'loss': '0.4989', 'grad_norm': '7.829', 'learning_rate': '8.34e-06', 'epoch': '1.249'}
|
| 108 |
+
{'loss': '0.5053', 'grad_norm': '2.903', 'learning_rate': '8.268e-06', 'epoch': '1.256'}
|
| 109 |
+
{'loss': '0.5081', 'grad_norm': '5.471', 'learning_rate': '8.196e-06', 'epoch': '1.262'}
|
| 110 |
+
{'loss': '0.496', 'grad_norm': '5.204', 'learning_rate': '8.124e-06', 'epoch': '1.269'}
|
| 111 |
+
{'loss': '0.5052', 'grad_norm': '4.377', 'learning_rate': '8.052e-06', 'epoch': '1.275'}
|
| 112 |
+
{'loss': '0.4984', 'grad_norm': '4.184', 'learning_rate': '7.98e-06', 'epoch': '1.282'}
|
| 113 |
+
{'loss': '0.4909', 'grad_norm': '4.991', 'learning_rate': '7.908e-06', 'epoch': '1.288'}
|
| 114 |
+
{'loss': '0.512', 'grad_norm': '3.76', 'learning_rate': '7.836e-06', 'epoch': '1.295'}
|
| 115 |
+
{'loss': '0.4873', 'grad_norm': '3.844', 'learning_rate': '7.764e-06', 'epoch': '1.301'}
|
| 116 |
+
{'loss': '0.4896', 'grad_norm': '6.987', 'learning_rate': '7.692e-06', 'epoch': '1.308'}
|
| 117 |
+
{'loss': '0.49', 'grad_norm': '6.267', 'learning_rate': '7.62e-06', 'epoch': '1.314'}
|
| 118 |
+
{'loss': '0.5036', 'grad_norm': '3.776', 'learning_rate': '7.548e-06', 'epoch': '1.321'}
|
| 119 |
+
{'loss': '0.4876', 'grad_norm': '3.42', 'learning_rate': '7.476e-06', 'epoch': '1.327'}
|
| 120 |
+
{'loss': '0.4705', 'grad_norm': '5.478', 'learning_rate': '7.404e-06', 'epoch': '1.334'}
|
| 121 |
+
{'loss': '0.4786', 'grad_norm': '3.313', 'learning_rate': '7.333e-06', 'epoch': '1.34'}
|
| 122 |
+
{'loss': '0.4998', 'grad_norm': '3.13', 'learning_rate': '7.261e-06', 'epoch': '1.347'}
|
| 123 |
+
{'loss': '0.4692', 'grad_norm': '3.971', 'learning_rate': '7.189e-06', 'epoch': '1.353'}
|
| 124 |
+
{'loss': '0.5064', 'grad_norm': '6.238', 'learning_rate': '7.117e-06', 'epoch': '1.36'}
|
| 125 |
+
{'eval_train_loss': '0.316', 'eval_dev-768_cosine_accuracy': '0.9788', 'eval_dev-512_cosine_accuracy': '0.979', 'eval_dev-256_cosine_accuracy': '0.979', 'eval_dev-128_cosine_accuracy': '0.9785', 'eval_dev-64_cosine_accuracy': '0.9774', 'eval_sequential_score': '0.9788', 'eval_train_runtime': '1.014e+04', 'eval_train_samples_per_second': '111.5', 'eval_train_steps_per_second': '13.93', 'epoch': '1.36'}
|
| 126 |
+
{'loss': '0.4925', 'grad_norm': '5.158', 'learning_rate': '7.045e-06', 'epoch': '1.366'}
|
| 127 |
+
{'loss': '0.4601', 'grad_norm': '4.139', 'learning_rate': '6.973e-06', 'epoch': '1.372'}
|
| 128 |
+
{'loss': '0.4762', 'grad_norm': '3.411', 'learning_rate': '6.901e-06', 'epoch': '1.379'}
|
| 129 |
+
{'loss': '0.4986', 'grad_norm': '4.23', 'learning_rate': '6.829e-06', 'epoch': '1.385'}
|
| 130 |
+
{'loss': '0.4656', 'grad_norm': '5.326', 'learning_rate': '6.757e-06', 'epoch': '1.392'}
|
| 131 |
+
{'loss': '0.4507', 'grad_norm': '3.826', 'learning_rate': '6.685e-06', 'epoch': '1.398'}
|
| 132 |
+
{'loss': '0.4862', 'grad_norm': '3.509', 'learning_rate': '6.613e-06', 'epoch': '1.405'}
|
| 133 |
+
{'loss': '0.4596', 'grad_norm': '4.734', 'learning_rate': '6.541e-06', 'epoch': '1.411'}
|
| 134 |
+
{'loss': '0.4696', 'grad_norm': '4.799', 'learning_rate': '6.469e-06', 'epoch': '1.418'}
|
| 135 |
+
{'loss': '0.4925', 'grad_norm': '4.942', 'learning_rate': '6.397e-06', 'epoch': '1.424'}
|
| 136 |
+
{'loss': '0.4796', 'grad_norm': '4.147', 'learning_rate': '6.325e-06', 'epoch': '1.431'}
|
| 137 |
+
{'loss': '0.4525', 'grad_norm': '5.146', 'learning_rate': '6.254e-06', 'epoch': '1.437'}
|
| 138 |
+
{'loss': '0.4717', 'grad_norm': '3.52', 'learning_rate': '6.182e-06', 'epoch': '1.444'}
|
| 139 |
+
{'loss': '0.4803', 'grad_norm': '3.25', 'learning_rate': '6.11e-06', 'epoch': '1.45'}
|
| 140 |
+
{'loss': '0.4675', 'grad_norm': '7.35', 'learning_rate': '6.038e-06', 'epoch': '1.457'}
|
| 141 |
+
{'loss': '0.4631', 'grad_norm': '3.847', 'learning_rate': '5.966e-06', 'epoch': '1.463'}
|
| 142 |
+
{'loss': '0.4622', 'grad_norm': '4.57', 'learning_rate': '5.894e-06', 'epoch': '1.47'}
|
| 143 |
+
{'loss': '0.4496', 'grad_norm': '1.997', 'learning_rate': '5.822e-06', 'epoch': '1.476'}
|
| 144 |
+
{'loss': '0.4678', 'grad_norm': '4.266', 'learning_rate': '5.75e-06', 'epoch': '1.483'}
|
| 145 |
+
{'loss': '0.4495', 'grad_norm': '5.948', 'learning_rate': '5.678e-06', 'epoch': '1.489'}
|
| 146 |
+
{'loss': '0.4474', 'grad_norm': '3.7', 'learning_rate': '5.606e-06', 'epoch': '1.495'}
|
| 147 |
+
{'loss': '0.4587', 'grad_norm': '2.877', 'learning_rate': '5.534e-06', 'epoch': '1.502'}
|
| 148 |
+
{'loss': '0.4591', 'grad_norm': '4.245', 'learning_rate': '5.462e-06', 'epoch': '1.508'}
|
| 149 |
+
{'loss': '0.4573', 'grad_norm': '5.431', 'learning_rate': '5.39e-06', 'epoch': '1.515'}
|
| 150 |
+
{'loss': '0.4442', 'grad_norm': '3.338', 'learning_rate': '5.318e-06', 'epoch': '1.521'}
|
| 151 |
+
{'loss': '0.455', 'grad_norm': '4.723', 'learning_rate': '5.246e-06', 'epoch': '1.528'}
|
| 152 |
+
{'loss': '0.4493', 'grad_norm': '4.226', 'learning_rate': '5.175e-06', 'epoch': '1.534'}
|
| 153 |
+
{'loss': '0.4485', 'grad_norm': '4.451', 'learning_rate': '5.103e-06', 'epoch': '1.541'}
|
| 154 |
+
{'loss': '0.4569', 'grad_norm': '4.297', 'learning_rate': '5.031e-06', 'epoch': '1.547'}
|
| 155 |
+
{'loss': '0.4346', 'grad_norm': '4.199', 'learning_rate': '4.959e-06', 'epoch': '1.554'}
|
| 156 |
+
{'eval_train_loss': '0.3001', 'eval_dev-768_cosine_accuracy': '0.9799', 'eval_dev-512_cosine_accuracy': '0.9802', 'eval_dev-256_cosine_accuracy': '0.9802', 'eval_dev-128_cosine_accuracy': '0.9798', 'eval_dev-64_cosine_accuracy': '0.9788', 'eval_sequential_score': '0.9799', 'eval_train_runtime': '1.008e+04', 'eval_train_samples_per_second': '112.1', 'eval_train_steps_per_second': '14.02', 'epoch': '1.554'}
|
| 157 |
+
{'loss': '0.4469', 'grad_norm': '3.364', 'learning_rate': '4.887e-06', 'epoch': '1.56'}
|
| 158 |
+
{'loss': '0.4602', 'grad_norm': '5.309', 'learning_rate': '4.815e-06', 'epoch': '1.567'}
|
| 159 |
+
{'loss': '0.443', 'grad_norm': '3.875', 'learning_rate': '4.743e-06', 'epoch': '1.573'}
|
| 160 |
+
{'loss': '0.4524', 'grad_norm': '4.824', 'learning_rate': '4.671e-06', 'epoch': '1.58'}
|
| 161 |
+
{'loss': '0.4528', 'grad_norm': '4.996', 'learning_rate': '4.599e-06', 'epoch': '1.586'}
|
| 162 |
+
{'loss': '0.4348', 'grad_norm': '4.96', 'learning_rate': '4.527e-06', 'epoch': '1.593'}
|
| 163 |
+
{'loss': '0.4533', 'grad_norm': '5.219', 'learning_rate': '4.455e-06', 'epoch': '1.599'}
|
| 164 |
+
{'loss': '0.4523', 'grad_norm': '3.444', 'learning_rate': '4.383e-06', 'epoch': '1.606'}
|
| 165 |
+
{'loss': '0.4509', 'grad_norm': '5.647', 'learning_rate': '4.311e-06', 'epoch': '1.612'}
|
| 166 |
+
{'loss': '0.4365', 'grad_norm': '5.052', 'learning_rate': '4.239e-06', 'epoch': '1.618'}
|
| 167 |
+
{'loss': '0.4504', 'grad_norm': '5.786', 'learning_rate': '4.167e-06', 'epoch': '1.625'}
|
| 168 |
+
{'loss': '0.4292', 'grad_norm': '4.353', 'learning_rate': '4.096e-06', 'epoch': '1.631'}
|
| 169 |
+
{'loss': '0.4406', 'grad_norm': '2.976', 'learning_rate': '4.024e-06', 'epoch': '1.638'}
|
| 170 |
+
{'loss': '0.4333', 'grad_norm': '3.685', 'learning_rate': '3.952e-06', 'epoch': '1.644'}
|
| 171 |
+
{'loss': '0.4361', 'grad_norm': '4.107', 'learning_rate': '3.88e-06', 'epoch': '1.651'}
|
| 172 |
+
{'loss': '0.4065', 'grad_norm': '3.636', 'learning_rate': '3.808e-06', 'epoch': '1.657'}
|
| 173 |
+
{'loss': '0.4671', 'grad_norm': '3.464', 'learning_rate': '3.736e-06', 'epoch': '1.664'}
|
| 174 |
+
{'loss': '0.4328', 'grad_norm': '3.129', 'learning_rate': '3.664e-06', 'epoch': '1.67'}
|
| 175 |
+
{'loss': '0.431', 'grad_norm': '2.453', 'learning_rate': '3.592e-06', 'epoch': '1.677'}
|
| 176 |
+
{'loss': '0.4523', 'grad_norm': '3.727', 'learning_rate': '3.52e-06', 'epoch': '1.683'}
|
| 177 |
+
{'loss': '0.4232', 'grad_norm': '4.398', 'learning_rate': '3.448e-06', 'epoch': '1.69'}
|
| 178 |
+
{'loss': '0.4257', 'grad_norm': '2.861', 'learning_rate': '3.376e-06', 'epoch': '1.696'}
|
| 179 |
+
{'loss': '0.4448', 'grad_norm': '3.523', 'learning_rate': '3.304e-06', 'epoch': '1.703'}
|
| 180 |
+
{'loss': '0.4491', 'grad_norm': '3.893', 'learning_rate': '3.232e-06', 'epoch': '1.709'}
|
| 181 |
+
{'loss': '0.4224', 'grad_norm': '3.399', 'learning_rate': '3.16e-06', 'epoch': '1.716'}
|
| 182 |
+
{'loss': '0.4297', 'grad_norm': '4.703', 'learning_rate': '3.088e-06', 'epoch': '1.722'}
|
| 183 |
+
{'loss': '0.4522', 'grad_norm': '4.29', 'learning_rate': '3.017e-06', 'epoch': '1.729'}
|
| 184 |
+
{'loss': '0.4195', 'grad_norm': '4.29', 'learning_rate': '2.945e-06', 'epoch': '1.735'}
|
| 185 |
+
{'loss': '0.4227', 'grad_norm': '3.841', 'learning_rate': '2.873e-06', 'epoch': '1.742'}
|
| 186 |
+
{'loss': '0.4381', 'grad_norm': '4.086', 'learning_rate': '2.801e-06', 'epoch': '1.748'}
|
| 187 |
+
{'eval_train_loss': '0.2875', 'eval_dev-768_cosine_accuracy': '0.9807', 'eval_dev-512_cosine_accuracy': '0.9808', 'eval_dev-256_cosine_accuracy': '0.9808', 'eval_dev-128_cosine_accuracy': '0.9805', 'eval_dev-64_cosine_accuracy': '0.9794', 'eval_sequential_score': '0.9807', 'eval_train_runtime': '1.012e+04', 'eval_train_samples_per_second': '111.6', 'eval_train_steps_per_second': '13.95', 'epoch': '1.748'}
|
| 188 |
+
{'loss': '0.446', 'grad_norm': '4.176', 'learning_rate': '2.729e-06', 'epoch': '1.754'}
|
| 189 |
+
{'loss': '0.426', 'grad_norm': '4.261', 'learning_rate': '2.657e-06', 'epoch': '1.761'}
|
| 190 |
+
{'loss': '0.4299', 'grad_norm': '4.676', 'learning_rate': '2.585e-06', 'epoch': '1.767'}
|
| 191 |
+
{'loss': '0.4247', 'grad_norm': '3.933', 'learning_rate': '2.513e-06', 'epoch': '1.774'}
|
| 192 |
+
{'loss': '0.4244', 'grad_norm': '4.853', 'learning_rate': '2.441e-06', 'epoch': '1.78'}
|
| 193 |
+
{'loss': '0.4185', 'grad_norm': '2.985', 'learning_rate': '2.369e-06', 'epoch': '1.787'}
|
| 194 |
+
{'loss': '0.4292', 'grad_norm': '3.804', 'learning_rate': '2.297e-06', 'epoch': '1.793'}
|
| 195 |
+
{'loss': '0.4468', 'grad_norm': '3.187', 'learning_rate': '2.225e-06', 'epoch': '1.8'}
|
| 196 |
+
{'loss': '0.4118', 'grad_norm': '4.004', 'learning_rate': '2.153e-06', 'epoch': '1.806'}
|
| 197 |
+
{'loss': '0.4306', 'grad_norm': '4.007', 'learning_rate': '2.081e-06', 'epoch': '1.813'}
|
| 198 |
+
{'loss': '0.4447', 'grad_norm': '4.323', 'learning_rate': '2.009e-06', 'epoch': '1.819'}
|
| 199 |
+
{'loss': '0.4147', 'grad_norm': '3.863', 'learning_rate': '1.938e-06', 'epoch': '1.826'}
|
| 200 |
+
{'loss': '0.4189', 'grad_norm': '4.788', 'learning_rate': '1.866e-06', 'epoch': '1.832'}
|
| 201 |
+
{'loss': '0.4167', 'grad_norm': '4.276', 'learning_rate': '1.794e-06', 'epoch': '1.839'}
|
| 202 |
+
{'loss': '0.4022', 'grad_norm': '3.887', 'learning_rate': '1.722e-06', 'epoch': '1.845'}
|
| 203 |
+
{'loss': '0.4158', 'grad_norm': '3.075', 'learning_rate': '1.65e-06', 'epoch': '1.852'}
|
| 204 |
+
{'loss': '0.4228', 'grad_norm': '3.993', 'learning_rate': '1.578e-06', 'epoch': '1.858'}
|
| 205 |
+
{'loss': '0.4256', 'grad_norm': '4.497', 'learning_rate': '1.506e-06', 'epoch': '1.865'}
|
| 206 |
+
{'loss': '0.4251', 'grad_norm': '4.539', 'learning_rate': '1.434e-06', 'epoch': '1.871'}
|
| 207 |
+
{'loss': '0.4232', 'grad_norm': '2.337', 'learning_rate': '1.362e-06', 'epoch': '1.877'}
|
| 208 |
+
{'loss': '0.4143', 'grad_norm': '3.389', 'learning_rate': '1.29e-06', 'epoch': '1.884'}
|
| 209 |
+
{'loss': '0.4331', 'grad_norm': '3.545', 'learning_rate': '1.218e-06', 'epoch': '1.89'}
|
| 210 |
+
{'loss': '0.4253', 'grad_norm': '5.606', 'learning_rate': '1.146e-06', 'epoch': '1.897'}
|
| 211 |
+
{'loss': '0.441', 'grad_norm': '4.453', 'learning_rate': '1.074e-06', 'epoch': '1.903'}
|
| 212 |
+
{'loss': '0.4337', 'grad_norm': '5.374', 'learning_rate': '1.002e-06', 'epoch': '1.91'}
|
| 213 |
+
{'loss': '0.4016', 'grad_norm': '2.246', 'learning_rate': '9.305e-07', 'epoch': '1.916'}
|
| 214 |
+
{'loss': '0.4249', 'grad_norm': '5.255', 'learning_rate': '8.585e-07', 'epoch': '1.923'}
|
| 215 |
+
{'loss': '0.4108', 'grad_norm': '3.59', 'learning_rate': '7.866e-07', 'epoch': '1.929'}
|
| 216 |
+
{'loss': '0.4272', 'grad_norm': '4.258', 'learning_rate': '7.147e-07', 'epoch': '1.936'}
|
| 217 |
+
{'loss': '0.3916', 'grad_norm': '3.476', 'learning_rate': '6.427e-07', 'epoch': '1.942'}
|
| 218 |
+
{'eval_train_loss': '0.2812', 'eval_dev-768_cosine_accuracy': '0.981', 'eval_dev-512_cosine_accuracy': '0.9811', 'eval_dev-256_cosine_accuracy': '0.9813', 'eval_dev-128_cosine_accuracy': '0.9811', 'eval_dev-64_cosine_accuracy': '0.9797', 'eval_sequential_score': '0.981', 'eval_train_runtime': '1.03e+04', 'eval_train_samples_per_second': '109.7', 'eval_train_steps_per_second': '13.71', 'epoch': '1.942'}
|
| 219 |
+
{'loss': '0.4334', 'grad_norm': '4.623', 'learning_rate': '5.708e-07', 'epoch': '1.949'}
|
| 220 |
+
{'loss': '0.4462', 'grad_norm': '5.31', 'learning_rate': '4.989e-07', 'epoch': '1.955'}
|
| 221 |
+
{'loss': '0.4436', 'grad_norm': '3.379', 'learning_rate': '4.269e-07', 'epoch': '1.962'}
|
| 222 |
+
{'loss': '0.4278', 'grad_norm': '5.471', 'learning_rate': '3.55e-07', 'epoch': '1.968'}
|
| 223 |
+
{'loss': '0.417', 'grad_norm': '3.435', 'learning_rate': '2.831e-07', 'epoch': '1.975'}
|
| 224 |
+
{'loss': '0.4376', 'grad_norm': '2.617', 'learning_rate': '2.111e-07', 'epoch': '1.981'}
|
| 225 |
+
{'loss': '0.4433', 'grad_norm': '3.465', 'learning_rate': '1.392e-07', 'epoch': '1.988'}
|
| 226 |
+
{'loss': '0.4292', 'grad_norm': '2.354', 'learning_rate': '6.726e-08', 'epoch': '1.994'}
|
| 227 |
+
{'train_runtime': '9.588e+04', 'train_samples_per_second': '82.48', 'train_steps_per_second': '0.644', 'train_loss': '0.403', 'epoch': '2'}
|
| 228 |
+
model saved successfully
|