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-task1-min_symbols_template_small-deepseek-coder-1.3b-base-ddp-2lr
+  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-task1-min_symbols_template_small-deepseek-coder-1.3b-base-ddp-2lr
+
+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: 0.2115
+
+## 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: 0.0002
+- 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 |
+|:-------------:|:-------:|:-----:|:---------------:|
+| 0.5172        | 0.2001  | 629   | 0.3780          |
+| 0.3747        | 0.4001  | 1258  | 0.3336          |
+| 0.3399        | 0.6002  | 1887  | 0.3039          |
+| 0.3014        | 0.8003  | 2516  | 0.2870          |
+| 0.2891        | 1.0003  | 3145  | 0.2798          |
+| 0.2721        | 1.2004  | 3774  | 0.2671          |
+| 0.2643        | 1.4004  | 4403  | 0.2577          |
+| 0.2522        | 1.6005  | 5032  | 0.2514          |
+| 0.2496        | 1.8006  | 5661  | 0.2455          |
+| 0.2426        | 2.0006  | 6290  | 0.2414          |
+| 0.2365        | 2.2007  | 6919  | 0.2360          |
+| 0.2267        | 2.4008  | 7548  | 0.2346          |
+| 0.2223        | 2.6008  | 8177  | 0.2306          |
+| 0.2225        | 2.8009  | 8806  | 0.2264          |
+| 0.218         | 3.0010  | 9435  | 0.2238          |
+| 0.2003        | 3.2010  | 10064 | 0.2245          |
+| 0.2015        | 3.4011  | 10693 | 0.2217          |
+| 0.2019        | 3.6011  | 11322 | 0.2167          |
+| 0.2           | 3.8012  | 11951 | 0.2136          |
+| 0.1991        | 4.0013  | 12580 | 0.2127          |
+| 0.1848        | 4.2013  | 13209 | 0.2149          |
+| 0.1831        | 4.4014  | 13838 | 0.2123          |
+| 0.1867        | 4.6015  | 14467 | 0.2114          |
+| 0.1819        | 4.8015  | 15096 | 0.2091          |
+| 0.1833        | 5.0016  | 15725 | 0.2065          |
+| 0.1741        | 5.2017  | 16354 | 0.2082          |
+| 0.1699        | 5.4017  | 16983 | 0.2067          |
+| 0.1689        | 5.6018  | 17612 | 0.2049          |
+| 0.1692        | 5.8018  | 18241 | 0.2029          |
+| 0.1703        | 6.0019  | 18870 | 0.2057          |
+| 0.1649        | 6.2020  | 19499 | 0.2055          |
+| 0.1563        | 6.4020  | 20128 | 0.2076          |
+| 0.1568        | 6.6021  | 20757 | 0.2033          |
+| 0.1559        | 6.8022  | 21386 | 0.2007          |
+| 0.159         | 7.0022  | 22015 | 0.2013          |
+| 0.1446        | 7.2023  | 22644 | 0.2051          |
+| 0.1455        | 7.4024  | 23273 | 0.2031          |
+| 0.147         | 7.6024  | 23902 | 0.2053          |
+| 0.1478        | 7.8025  | 24531 | 0.1988          |
+| 0.1462        | 8.0025  | 25160 | 0.2023          |
+| 0.1371        | 8.2026  | 25789 | 0.2073          |
+| 0.1374        | 8.4027  | 26418 | 0.2018          |
+| 0.1382        | 8.6027  | 27047 | 0.2013          |
+| 0.136         | 8.8028  | 27676 | 0.2036          |
+| 0.1396        | 9.0029  | 28305 | 0.2004          |
+| 0.1335        | 9.2029  | 28934 | 0.2069          |
+| 0.1278        | 9.4030  | 29563 | 0.2079          |
+| 0.1295        | 9.6031  | 30192 | 0.2053          |
+| 0.1303        | 9.8031  | 30821 | 0.2066          |
+| 0.129         | 10.0032 | 31450 | 0.2040          |
+| 0.1208        | 10.2032 | 32079 | 0.2099          |
+| 0.1219        | 10.4033 | 32708 | 0.2096          |
+| 0.1219        | 10.6034 | 33337 | 0.2105          |
+| 0.1217        | 10.8034 | 33966 | 0.2082          |
+| 0.1208        | 11.0035 | 34595 | 0.2093          |
+| 0.1181        | 11.2036 | 35224 | 0.2118          |
+| 0.1154        | 11.4036 | 35853 | 0.2144          |
+| 0.115         | 11.6037 | 36482 | 0.2130          |
+| 0.1156        | 11.8038 | 37111 | 0.2115          |
+
+
+### 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:c97fdca213661a02ef2feacd877e07554c1d6ae0118ca7ae5f3a126ebca35a21
+size 6304096

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89bedacf265fac829eb2dd7adcf9ac7fd053d3a6a58c175b8afca01bb68f5e67
+size 5496