Model save

README.md

@@ -0,0 +1,94 @@
+---
+library_name: transformers
+license: llama3.1
+base_model: meta-llama/Llama-3.1-8B-Instruct
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: crafting_sft_fail_new_mem
+  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. -->
+
+# crafting_sft_fail_new_mem
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3203
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- 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
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5344        | 0.0323 | 50   | 0.4756          |
+| 0.528         | 0.0646 | 100  | 0.4853          |
+| 0.5123        | 0.0969 | 150  | 0.4897          |
+| 0.522         | 0.1291 | 200  | 0.4982          |
+| 0.5227        | 0.1614 | 250  | 0.4605          |
+| 0.5095        | 0.1937 | 300  | 0.4482          |
+| 0.4733        | 0.2260 | 350  | 0.4402          |
+| 0.47          | 0.2583 | 400  | 0.4243          |
+| 0.4815        | 0.2906 | 450  | 0.4186          |
+| 0.4526        | 0.3229 | 500  | 0.4181          |
+| 0.4706        | 0.3552 | 550  | 0.4096          |
+| 0.4523        | 0.3874 | 600  | 0.3973          |
+| 0.4675        | 0.4197 | 650  | 0.4003          |
+| 0.4389        | 0.4520 | 700  | 0.3848          |
+| 0.4385        | 0.4843 | 750  | 0.3801          |
+| 0.4312        | 0.5166 | 800  | 0.3762          |
+| 0.4103        | 0.5489 | 850  | 0.3642          |
+| 0.4106        | 0.5812 | 900  | 0.3626          |
+| 0.3937        | 0.6134 | 950  | 0.3584          |
+| 0.4053        | 0.6457 | 1000 | 0.3481          |
+| 0.3764        | 0.6780 | 1050 | 0.3426          |
+| 0.3712        | 0.7103 | 1100 | 0.3413          |
+| 0.3721        | 0.7426 | 1150 | 0.3354          |
+| 0.3561        | 0.7749 | 1200 | 0.3320          |
+| 0.3788        | 0.8072 | 1250 | 0.3286          |
+| 0.3673        | 0.8395 | 1300 | 0.3256          |
+| 0.3561        | 0.8717 | 1350 | 0.3227          |
+| 0.3648        | 0.9040 | 1400 | 0.3217          |
+| 0.3789        | 0.9363 | 1450 | 0.3205          |
+| 0.369         | 0.9686 | 1500 | 0.3203          |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.49.0"
+}