Model save

README.md

@@ -0,0 +1,79 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-Coder-3B-Instruct
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-3B-Instruct
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: SFT-Qwen2.5-Coder-3B_v1.2s
+  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. -->
+
+# SFT-Qwen2.5-Coder-3B_v1.2s
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4859
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9411        | 0.1985 | 20   | 0.7566          |
+| 0.7658        | 0.3970 | 40   | 0.6418          |
+| 0.6313        | 0.5955 | 60   | 0.5926          |
+| 0.6186        | 0.7940 | 80   | 0.5650          |
+| 0.5868        | 0.9926 | 100  | 0.5429          |
+| 0.467         | 1.1886 | 120  | 0.5286          |
+| 0.5086        | 1.3871 | 140  | 0.5205          |
+| 0.4747        | 1.5856 | 160  | 0.5111          |
+| 0.4872        | 1.7841 | 180  | 0.5012          |
+| 0.5184        | 1.9826 | 200  | 0.4954          |
+| 0.404         | 2.1787 | 220  | 0.5021          |
+| 0.3772        | 2.3772 | 240  | 0.5040          |
+| 0.4188        | 2.5757 | 260  | 0.4901          |
+| 0.446         | 2.7742 | 280  | 0.4885          |
+| 0.4378        | 2.9727 | 300  | 0.4859          |
+
+
+### Framework versions
+
+- PEFT 0.18.0
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
+- Datasets 4.4.1
+- Tokenizers 0.22.1

trainer_state.json

@@ -0,0 +1,285 @@
+{
+  "best_global_step": 300,
+  "best_metric": 0.48589417338371277,
+  "best_model_checkpoint": "j05hr3d/SFT-Qwen2.5-Coder-3B_v1.2s/checkpoint-300",
+  "epoch": 3.0,
+  "eval_steps": 20,
+  "global_step": 303,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19851116625310175,
+      "grad_norm": 0.41667449474334717,
+      "learning_rate": 9.69283276450512e-05,
+      "loss": 0.9411,
+      "step": 20
+    },
+    {
+      "epoch": 0.19851116625310175,
+      "eval_loss": 0.7566442489624023,
+      "eval_runtime": 10.3526,
+      "eval_samples_per_second": 8.5,
+      "eval_steps_per_second": 4.25,
+      "step": 20
+    },
+    {
+      "epoch": 0.3970223325062035,
+      "grad_norm": 1.0499056577682495,
+      "learning_rate": 9.01023890784983e-05,
+      "loss": 0.7658,
+      "step": 40
+    },
+    {
+      "epoch": 0.3970223325062035,
+      "eval_loss": 0.6418420672416687,
+      "eval_runtime": 10.1798,
+      "eval_samples_per_second": 8.645,
+      "eval_steps_per_second": 4.322,
+      "step": 40
+    },
+    {
+      "epoch": 0.5955334987593052,
+      "grad_norm": 0.6770362854003906,
+      "learning_rate": 8.32764505119454e-05,
+      "loss": 0.6313,
+      "step": 60
+    },
+    {
+      "epoch": 0.5955334987593052,
+      "eval_loss": 0.5925782918930054,
+      "eval_runtime": 10.2985,
+      "eval_samples_per_second": 8.545,
+      "eval_steps_per_second": 4.272,
+      "step": 60
+    },
+    {
+      "epoch": 0.794044665012407,
+      "grad_norm": 0.48328474164009094,
+      "learning_rate": 7.64505119453925e-05,
+      "loss": 0.6186,
+      "step": 80
+    },
+    {
+      "epoch": 0.794044665012407,
+      "eval_loss": 0.5649975538253784,
+      "eval_runtime": 10.3541,
+      "eval_samples_per_second": 8.499,
+      "eval_steps_per_second": 4.25,
+      "step": 80
+    },
+    {
+      "epoch": 0.9925558312655087,
+      "grad_norm": 0.6009169220924377,
+      "learning_rate": 6.96245733788396e-05,
+      "loss": 0.5868,
+      "step": 100
+    },
+    {
+      "epoch": 0.9925558312655087,
+      "eval_loss": 0.5429486632347107,
+      "eval_runtime": 10.362,
+      "eval_samples_per_second": 8.493,
+      "eval_steps_per_second": 4.246,
+      "step": 100
+    },
+    {
+      "epoch": 1.1885856079404467,
+      "grad_norm": 0.5405522584915161,
+      "learning_rate": 6.27986348122867e-05,
+      "loss": 0.467,
+      "step": 120
+    },
+    {
+      "epoch": 1.1885856079404467,
+      "eval_loss": 0.5285952091217041,
+      "eval_runtime": 10.3349,
+      "eval_samples_per_second": 8.515,
+      "eval_steps_per_second": 4.257,
+      "step": 120
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 0.6942219138145447,
+      "learning_rate": 5.597269624573379e-05,
+      "loss": 0.5086,
+      "step": 140
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "eval_loss": 0.5205278992652893,
+      "eval_runtime": 10.405,
+      "eval_samples_per_second": 8.457,
+      "eval_steps_per_second": 4.229,
+      "step": 140
+    },
+    {
+      "epoch": 1.58560794044665,
+      "grad_norm": 0.47721970081329346,
+      "learning_rate": 4.914675767918089e-05,
+      "loss": 0.4747,
+      "step": 160
+    },
+    {
+      "epoch": 1.58560794044665,
+      "eval_loss": 0.5111103653907776,
+      "eval_runtime": 10.4065,
+      "eval_samples_per_second": 8.456,
+      "eval_steps_per_second": 4.228,
+      "step": 160
+    },
+    {
+      "epoch": 1.7841191066997517,
+      "grad_norm": 0.5524210929870605,
+      "learning_rate": 4.2320819112627994e-05,
+      "loss": 0.4872,
+      "step": 180
+    },
+    {
+      "epoch": 1.7841191066997517,
+      "eval_loss": 0.5011650919914246,
+      "eval_runtime": 10.3583,
+      "eval_samples_per_second": 8.496,
+      "eval_steps_per_second": 4.248,
+      "step": 180
+    },
+    {
+      "epoch": 1.9826302729528535,
+      "grad_norm": 0.5560195446014404,
+      "learning_rate": 3.549488054607509e-05,
+      "loss": 0.5184,
+      "step": 200
+    },
+    {
+      "epoch": 1.9826302729528535,
+      "eval_loss": 0.4954199492931366,
+      "eval_runtime": 10.341,
+      "eval_samples_per_second": 8.51,
+      "eval_steps_per_second": 4.255,
+      "step": 200
+    },
+    {
+      "epoch": 2.1786600496277915,
+      "grad_norm": 0.7221893668174744,
+      "learning_rate": 2.8668941979522183e-05,
+      "loss": 0.404,
+      "step": 220
+    },
+    {
+      "epoch": 2.1786600496277915,
+      "eval_loss": 0.5021213293075562,
+      "eval_runtime": 10.3777,
+      "eval_samples_per_second": 8.48,
+      "eval_steps_per_second": 4.24,
+      "step": 220
+    },
+    {
+      "epoch": 2.3771712158808933,
+      "grad_norm": 0.7171949744224548,
+      "learning_rate": 2.1843003412969286e-05,
+      "loss": 0.3772,
+      "step": 240
+    },
+    {
+      "epoch": 2.3771712158808933,
+      "eval_loss": 0.5039552450180054,
+      "eval_runtime": 10.3559,
+      "eval_samples_per_second": 8.498,
+      "eval_steps_per_second": 4.249,
+      "step": 240
+    },
+    {
+      "epoch": 2.575682382133995,
+      "grad_norm": 0.6108347773551941,
+      "learning_rate": 1.5017064846416384e-05,
+      "loss": 0.4188,
+      "step": 260
+    },
+    {
+      "epoch": 2.575682382133995,
+      "eval_loss": 0.49007371068000793,
+      "eval_runtime": 10.3489,
+      "eval_samples_per_second": 8.503,
+      "eval_steps_per_second": 4.252,
+      "step": 260
+    },
+    {
+      "epoch": 2.774193548387097,
+      "grad_norm": 0.866223931312561,
+      "learning_rate": 8.191126279863482e-06,
+      "loss": 0.446,
+      "step": 280
+    },
+    {
+      "epoch": 2.774193548387097,
+      "eval_loss": 0.48849764466285706,
+      "eval_runtime": 10.31,
+      "eval_samples_per_second": 8.535,
+      "eval_steps_per_second": 4.268,
+      "step": 280
+    },
+    {
+      "epoch": 2.9727047146401984,
+      "grad_norm": 0.4195428490638733,
+      "learning_rate": 1.3651877133105804e-06,
+      "loss": 0.4378,
+      "step": 300
+    },
+    {
+      "epoch": 2.9727047146401984,
+      "eval_loss": 0.48589417338371277,
+      "eval_runtime": 10.443,
+      "eval_samples_per_second": 8.427,
+      "eval_steps_per_second": 4.213,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "step": 303,
+      "total_flos": 3.105581542121472e+16,
+      "train_loss": 0.5361647474096947,
+      "train_runtime": 1239.6629,
+      "train_samples_per_second": 1.951,
+      "train_steps_per_second": 0.244
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.48589417338371277,
+      "eval_runtime": 10.3992,
+      "eval_samples_per_second": 8.462,
+      "eval_steps_per_second": 4.231,
+      "step": 303
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 303,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.105581542121472e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}