End of training

README.md

@@ -0,0 +1,122 @@
+---
+library_name: peft
+license: other
+base_model: deepseek-ai/deepseek-coder-1.3b-base
+tags:
+- generated_from_trainer
+model-index:
+- name: lemexp-task2-unordered_template_small-deepseek-coder-1.3b-base-ddp-8lr
+  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. -->
+
+# lemexp-task2-unordered_template_small-deepseek-coder-1.3b-base-ddp-8lr
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2327
+
+## 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: 0.0008
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 12
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss |
+|:-------------:|:-------:|:-----:|:---------------:|
+| 0.4681        | 0.2001  | 629   | 0.3776          |
+| 0.379         | 0.4001  | 1258  | 0.3465          |
+| 0.3592        | 0.6002  | 1887  | 0.3382          |
+| 0.334         | 0.8003  | 2516  | 0.3192          |
+| 0.3264        | 1.0003  | 3145  | 0.3150          |
+| 0.3122        | 1.2004  | 3774  | 0.3127          |
+| 0.3073        | 1.4004  | 4403  | 0.3033          |
+| 0.2982        | 1.6005  | 5032  | 0.2978          |
+| 0.2974        | 1.8006  | 5661  | 0.2936          |
+| 0.2911        | 2.0006  | 6290  | 0.2884          |
+| 0.2871        | 2.2007  | 6919  | 0.2861          |
+| 0.2803        | 2.4008  | 7548  | 0.2783          |
+| 0.277         | 2.6008  | 8177  | 0.2820          |
+| 0.2778        | 2.8009  | 8806  | 0.2738          |
+| 0.272         | 3.0010  | 9435  | 0.2729          |
+| 0.2578        | 3.2010  | 10064 | 0.2702          |
+| 0.2596        | 3.4011  | 10693 | 0.2718          |
+| 0.2586        | 3.6011  | 11322 | 0.2648          |
+| 0.257         | 3.8012  | 11951 | 0.2595          |
+| 0.2577        | 4.0013  | 12580 | 0.2591          |
+| 0.2431        | 4.2013  | 13209 | 0.2589          |
+| 0.2401        | 4.4014  | 13838 | 0.2598          |
+| 0.2445        | 4.6015  | 14467 | 0.2537          |
+| 0.2403        | 4.8015  | 15096 | 0.2544          |
+| 0.2405        | 5.0016  | 15725 | 0.2535          |
+| 0.2311        | 5.2017  | 16354 | 0.2533          |
+| 0.227         | 5.4017  | 16983 | 0.2508          |
+| 0.2259        | 5.6018  | 17612 | 0.2450          |
+| 0.2238        | 5.8018  | 18241 | 0.2445          |
+| 0.2254        | 6.0019  | 18870 | 0.2419          |
+| 0.2201        | 6.2020  | 19499 | 0.2426          |
+| 0.2096        | 6.4020  | 20128 | 0.2432          |
+| 0.2088        | 6.6021  | 20757 | 0.2440          |
+| 0.2078        | 6.8022  | 21386 | 0.2386          |
+| 0.2114        | 7.0022  | 22015 | 0.2388          |
+| 0.1919        | 7.2023  | 22644 | 0.2388          |
+| 0.1939        | 7.4024  | 23273 | 0.2351          |
+| 0.1947        | 7.6024  | 23902 | 0.2330          |
+| 0.1939        | 7.8025  | 24531 | 0.2283          |
+| 0.1916        | 8.0025  | 25160 | 0.2262          |
+| 0.179         | 8.2026  | 25789 | 0.2330          |
+| 0.1784        | 8.4027  | 26418 | 0.2311          |
+| 0.1781        | 8.6027  | 27047 | 0.2327          |
+| 0.1772        | 8.8028  | 27676 | 0.2260          |
+| 0.1783        | 9.0029  | 28305 | 0.2234          |
+| 0.1688        | 9.2029  | 28934 | 0.2323          |
+| 0.1607        | 9.4030  | 29563 | 0.2269          |
+| 0.1613        | 9.6031  | 30192 | 0.2249          |
+| 0.1622        | 9.8031  | 30821 | 0.2253          |
+| 0.1602        | 10.0032 | 31450 | 0.2239          |
+| 0.1444        | 10.2032 | 32079 | 0.2283          |
+| 0.1461        | 10.4033 | 32708 | 0.2281          |
+| 0.1449        | 10.6034 | 33337 | 0.2282          |
+| 0.1455        | 10.8034 | 33966 | 0.2232          |
+| 0.1431        | 11.0035 | 34595 | 0.2277          |
+| 0.1334        | 11.2036 | 35224 | 0.2302          |
+| 0.1304        | 11.4036 | 35853 | 0.2322          |
+| 0.1304        | 11.6037 | 36482 | 0.2313          |
+| 0.1291        | 11.8038 | 37111 | 0.2327          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ef006a61b6f1ff6d157eecfee43651d6fdcdf62accbf7d507c09e31b21a1711
+size 6304096

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4c12577dee2db943aa7ea39f0c2e265bafeb42d57fe47b279ec442a90bdc14
+size 5496