End of training

README.md

@@ -0,0 +1,123 @@
+---
+library_name: peft
+license: other
+base_model: deepseek-ai/deepseek-coder-6.7b-base
+tags:
+- generated_from_trainer
+model-index:
+- name: small-4e4
+  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. -->
+
+# small-4e4
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1423
+
+## 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: 0.0004
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- 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 |
+|:-------------:|:-------:|:-----:|:---------------:|
+| 0.5879        | 0.2001  | 720   | 0.1971          |
+| 0.3956        | 0.4002  | 1440  | 0.1700          |
+| 0.3301        | 0.6003  | 2160  | 0.1580          |
+| 0.3136        | 0.8003  | 2880  | 0.1479          |
+| 0.2909        | 1.0003  | 3600  | 0.1407          |
+| 0.2581        | 1.2004  | 4320  | 0.1371          |
+| 0.25          | 1.4004  | 5040  | 0.1318          |
+| 0.2472        | 1.6005  | 5760  | 0.1324          |
+| 0.2456        | 1.8006  | 6480  | 0.1266          |
+| 0.2376        | 2.0006  | 7200  | 0.1232          |
+| 0.2128        | 2.2006  | 7920  | 0.1262          |
+| 0.2067        | 2.4007  | 8640  | 0.1207          |
+| 0.2026        | 2.6008  | 9360  | 0.1207          |
+| 0.2016        | 2.8009  | 10080 | 0.1171          |
+| 0.2031        | 3.0008  | 10800 | 0.1149          |
+| 0.1711        | 3.2009  | 11520 | 0.1167          |
+| 0.1758        | 3.4010  | 12240 | 0.1127          |
+| 0.1743        | 3.6011  | 12960 | 0.1138          |
+| 0.1728        | 3.8012  | 13680 | 0.1133          |
+| 0.1732        | 4.0011  | 14400 | 0.1100          |
+| 0.1464        | 4.2012  | 15120 | 0.1110          |
+| 0.1491        | 4.4013  | 15840 | 0.1109          |
+| 0.148         | 4.6014  | 16560 | 0.1095          |
+| 0.1504        | 4.8014  | 17280 | 0.1072          |
+| 0.1465        | 5.0014  | 18000 | 0.1076          |
+| 0.1239        | 5.2015  | 18720 | 0.1118          |
+| 0.1267        | 5.4016  | 19440 | 0.1111          |
+| 0.1289        | 5.6016  | 20160 | 0.1070          |
+| 0.1315        | 5.8017  | 20880 | 0.1080          |
+| 0.1269        | 6.0017  | 21600 | 0.1057          |
+| 0.1103        | 6.2018  | 22320 | 0.1098          |
+| 0.1101        | 6.4018  | 23040 | 0.1113          |
+| 0.1111        | 6.6019  | 23760 | 0.1092          |
+| 0.1112        | 6.8020  | 24480 | 0.1077          |
+| 0.1112        | 7.0019  | 25200 | 0.1076          |
+| 0.0966        | 7.2020  | 25920 | 0.1135          |
+| 0.0933        | 7.4021  | 26640 | 0.1152          |
+| 0.0948        | 7.6022  | 27360 | 0.1155          |
+| 0.094         | 7.8023  | 28080 | 0.1074          |
+| 0.0948        | 8.0022  | 28800 | 0.1102          |
+| 0.0789        | 8.2023  | 29520 | 0.1151          |
+| 0.0772        | 8.4024  | 30240 | 0.1126          |
+| 0.0782        | 8.6025  | 30960 | 0.1149          |
+| 0.0802        | 8.8026  | 31680 | 0.1156          |
+| 0.079         | 9.0025  | 32400 | 0.1141          |
+| 0.0646        | 9.2026  | 33120 | 0.1249          |
+| 0.0663        | 9.4027  | 33840 | 0.1176          |
+| 0.0671        | 9.6028  | 34560 | 0.1227          |
+| 0.0689        | 9.8028  | 35280 | 0.1210          |
+| 0.0659        | 10.0028 | 36000 | 0.1210          |
+| 0.0561        | 10.2029 | 36720 | 0.1304          |
+| 0.0556        | 10.4029 | 37440 | 0.1302          |
+| 0.0568        | 10.6030 | 38160 | 0.1321          |
+| 0.0564        | 10.8031 | 38880 | 0.1299          |
+| 0.0581        | 11.0031 | 39600 | 0.1314          |
+| 0.0505        | 11.2031 | 40320 | 0.1403          |
+| 0.0494        | 11.4032 | 41040 | 0.1426          |
+| 0.0495        | 11.6033 | 41760 | 0.1414          |
+| 0.0498        | 11.8034 | 42480 | 0.1423          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-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": [
+    "q_proj",
+    "v_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 sha256:5c25a1a33987743a30fe7ca963d0190b27ac3e87a7fa017aabfb54bef39b2ecf
+size 541459256

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39c77abc9b79e41320c1b31198c8a780bb3b28b86e08cdfd5e4327edf0635ca
+size 5368