Model save

README.md

@@ -0,0 +1,77 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: SFT-Qwen2.5-Coder-7B_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-7B_v1.2s
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5014
+
+## 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: 8
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8618        | 0.1985 | 20   | 0.7028          |
+| 0.6786        | 0.3970 | 40   | 0.6255          |
+| 0.5624        | 0.5955 | 60   | 0.5838          |
+| 0.5455        | 0.7940 | 80   | 0.5579          |
+| 0.531         | 0.9926 | 100  | 0.5395          |
+| 0.3587        | 1.1886 | 120  | 0.5308          |
+| 0.4215        | 1.3871 | 140  | 0.5241          |
+| 0.4159        | 1.5856 | 160  | 0.5155          |
+| 0.4262        | 1.7841 | 180  | 0.5045          |
+| 0.4629        | 1.9826 | 200  | 0.5014          |
+| 0.344         | 2.1787 | 220  | 0.5186          |
+| 0.3075        | 2.3772 | 240  | 0.5144          |
+| 0.3312        | 2.5757 | 260  | 0.5061          |
+
+
+### Framework versions
+
+- PEFT 0.18.0
+- Transformers 4.57.3
+- Pytorch 2.9.0+cu126
+- Datasets 4.4.1
+- Tokenizers 0.22.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3057242310254f578ccdd138bfed081171292f5efc734bc59d7472021e4490d
+oid sha256:7e934042b4437988c6afbfda9a2224074550f6116ea42aafa7136869c2a1e580
 size 323014168

trainer_state.json

@@ -0,0 +1,255 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.5014212727546692,
+  "best_model_checkpoint": "j05hr3d/SFT-Qwen2.5-Coder-7B_v1.2s/checkpoint-200",
+  "epoch": 2.575682382133995,
+  "eval_steps": 20,
+  "global_step": 260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19851116625310175,
+      "grad_norm": 0.3443014621734619,
+      "learning_rate": 9.69283276450512e-05,
+      "loss": 0.8618,
+      "step": 20
+    },
+    {
+      "epoch": 0.19851116625310175,
+      "eval_loss": 0.7027769088745117,
+      "eval_runtime": 17.556,
+      "eval_samples_per_second": 5.013,
+      "eval_steps_per_second": 0.627,
+      "step": 20
+    },
+    {
+      "epoch": 0.3970223325062035,
+      "grad_norm": 0.5014017224311829,
+      "learning_rate": 9.01023890784983e-05,
+      "loss": 0.6786,
+      "step": 40
+    },
+    {
+      "epoch": 0.3970223325062035,
+      "eval_loss": 0.6255155801773071,
+      "eval_runtime": 16.528,
+      "eval_samples_per_second": 5.324,
+      "eval_steps_per_second": 0.666,
+      "step": 40
+    },
+    {
+      "epoch": 0.5955334987593052,
+      "grad_norm": 0.5878388285636902,
+      "learning_rate": 8.32764505119454e-05,
+      "loss": 0.5624,
+      "step": 60
+    },
+    {
+      "epoch": 0.5955334987593052,
+      "eval_loss": 0.583770751953125,
+      "eval_runtime": 16.5394,
+      "eval_samples_per_second": 5.321,
+      "eval_steps_per_second": 0.665,
+      "step": 60
+    },
+    {
+      "epoch": 0.794044665012407,
+      "grad_norm": 0.46020567417144775,
+      "learning_rate": 7.64505119453925e-05,
+      "loss": 0.5455,
+      "step": 80
+    },
+    {
+      "epoch": 0.794044665012407,
+      "eval_loss": 0.5578548908233643,
+      "eval_runtime": 16.5174,
+      "eval_samples_per_second": 5.328,
+      "eval_steps_per_second": 0.666,
+      "step": 80
+    },
+    {
+      "epoch": 0.9925558312655087,
+      "grad_norm": 0.5035529732704163,
+      "learning_rate": 6.96245733788396e-05,
+      "loss": 0.531,
+      "step": 100
+    },
+    {
+      "epoch": 0.9925558312655087,
+      "eval_loss": 0.5394544005393982,
+      "eval_runtime": 16.5148,
+      "eval_samples_per_second": 5.329,
+      "eval_steps_per_second": 0.666,
+      "step": 100
+    },
+    {
+      "epoch": 1.1885856079404467,
+      "grad_norm": 0.4639776945114136,
+      "learning_rate": 6.27986348122867e-05,
+      "loss": 0.3587,
+      "step": 120
+    },
+    {
+      "epoch": 1.1885856079404467,
+      "eval_loss": 0.5307751297950745,
+      "eval_runtime": 16.5265,
+      "eval_samples_per_second": 5.325,
+      "eval_steps_per_second": 0.666,
+      "step": 120
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "grad_norm": 0.6005762219429016,
+      "learning_rate": 5.597269624573379e-05,
+      "loss": 0.4215,
+      "step": 140
+    },
+    {
+      "epoch": 1.3870967741935485,
+      "eval_loss": 0.5240680575370789,
+      "eval_runtime": 16.5234,
+      "eval_samples_per_second": 5.326,
+      "eval_steps_per_second": 0.666,
+      "step": 140
+    },
+    {
+      "epoch": 1.58560794044665,
+      "grad_norm": 0.4485836625099182,
+      "learning_rate": 4.914675767918089e-05,
+      "loss": 0.4159,
+      "step": 160
+    },
+    {
+      "epoch": 1.58560794044665,
+      "eval_loss": 0.5154905915260315,
+      "eval_runtime": 16.5373,
+      "eval_samples_per_second": 5.321,
+      "eval_steps_per_second": 0.665,
+      "step": 160
+    },
+    {
+      "epoch": 1.7841191066997517,
+      "grad_norm": 0.5078586339950562,
+      "learning_rate": 4.2320819112627994e-05,
+      "loss": 0.4262,
+      "step": 180
+    },
+    {
+      "epoch": 1.7841191066997517,
+      "eval_loss": 0.5044925212860107,
+      "eval_runtime": 16.5208,
+      "eval_samples_per_second": 5.327,
+      "eval_steps_per_second": 0.666,
+      "step": 180
+    },
+    {
+      "epoch": 1.9826302729528535,
+      "grad_norm": 0.5249742269515991,
+      "learning_rate": 3.549488054607509e-05,
+      "loss": 0.4629,
+      "step": 200
+    },
+    {
+      "epoch": 1.9826302729528535,
+      "eval_loss": 0.5014212727546692,
+      "eval_runtime": 16.5224,
+      "eval_samples_per_second": 5.326,
+      "eval_steps_per_second": 0.666,
+      "step": 200
+    },
+    {
+      "epoch": 2.1786600496277915,
+      "grad_norm": 0.7255989909172058,
+      "learning_rate": 2.8668941979522183e-05,
+      "loss": 0.344,
+      "step": 220
+    },
+    {
+      "epoch": 2.1786600496277915,
+      "eval_loss": 0.5186240673065186,
+      "eval_runtime": 16.5239,
+      "eval_samples_per_second": 5.326,
+      "eval_steps_per_second": 0.666,
+      "step": 220
+    },
+    {
+      "epoch": 2.3771712158808933,
+      "grad_norm": 0.6361181735992432,
+      "learning_rate": 2.1843003412969286e-05,
+      "loss": 0.3075,
+      "step": 240
+    },
+    {
+      "epoch": 2.3771712158808933,
+      "eval_loss": 0.5144491195678711,
+      "eval_runtime": 16.5231,
+      "eval_samples_per_second": 5.326,
+      "eval_steps_per_second": 0.666,
+      "step": 240
+    },
+    {
+      "epoch": 2.575682382133995,
+      "grad_norm": 0.5754724144935608,
+      "learning_rate": 1.5017064846416384e-05,
+      "loss": 0.3312,
+      "step": 260
+    },
+    {
+      "epoch": 2.575682382133995,
+      "eval_loss": 0.5061134696006775,
+      "eval_runtime": 16.5426,
+      "eval_samples_per_second": 5.32,
+      "eval_steps_per_second": 0.665,
+      "step": 260
+    },
+    {
+      "epoch": 2.575682382133995,
+      "step": 260,
+      "total_flos": 6.698169255614054e+16,
+      "train_loss": 0.4805432246281551,
+      "train_runtime": 1183.0888,
+      "train_samples_per_second": 2.044,
+      "train_steps_per_second": 0.256
+    },
+    {
+      "epoch": 2.575682382133995,
+      "eval_loss": 0.5014212727546692,
+      "eval_runtime": 16.4919,
+      "eval_samples_per_second": 5.336,
+      "eval_steps_per_second": 0.667,
+      "step": 260
+    }
+  ],
+  "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": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.698169255614054e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}