Model save

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: s1k-11-test-192
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# s1k-11-test-192
+
+This model was trained from scratch on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 24
+- total_train_batch_size: 96
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

wandb/run-20250412_234030-6n803w1v/files/output.log

@@ -38,3 +38,17 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 100%|██████████| 2/2 [06:35<00:00, 197.55s/it]
 {'train_runtime': 396.7392, 'train_samples_per_second': 0.484, 'train_steps_per_second': 0.005, 'train_loss': 1.2243931889533997, 'epoch': 1.0}
 [INFO|trainer.py:4582] 2025-04-12 23:47:06,174 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3801] 2025-04-12 23:53:29,854 >> Saving model checkpoint to /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192
+[INFO|configuration_utils.py:414] 2025-04-12 23:53:29,859 >> Configuration saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/config.json
+[INFO|configuration_utils.py:865] 2025-04-12 23:53:29,861 >> Configuration saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/generation_config.json
+[INFO|modeling_utils.py:3043] 2025-04-12 23:53:44,718 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/model.safetensors.index.json.
+[INFO|tokenization_utils_base.py:2646] 2025-04-12 23:53:44,721 >> tokenizer config file saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2655] 2025-04-12 23:53:44,722 >> Special tokens file saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/special_tokens_map.json
+[INFO|trainer.py:3801] 2025-04-12 23:53:47,051 >> Saving model checkpoint to /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192
+[INFO|configuration_utils.py:414] 2025-04-12 23:53:47,056 >> Configuration saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/config.json
+[INFO|configuration_utils.py:865] 2025-04-12 23:53:47,057 >> Configuration saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/generation_config.json
+[INFO|modeling_utils.py:3043] 2025-04-12 23:54:02,164 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/model.safetensors.index.json.
+[INFO|tokenization_utils_base.py:2646] 2025-04-12 23:54:02,166 >> tokenizer config file saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2655] 2025-04-12 23:54:02,167 >> Special tokens file saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/special_tokens_map.json
+[INFO|modelcard.py:449] 2025-04-12 23:54:02,290 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}