Model save

README.md

@@ -0,0 +1,74 @@
+---
+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_v6
+  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_v6
+
+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: 0.9536
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.064         | 0.2974 | 20   | 1.0908          |
+| 0.8857        | 0.5948 | 40   | 1.0361          |
+| 0.8355        | 0.8922 | 60   | 1.0029          |
+| 0.7792        | 1.1784 | 80   | 0.9860          |
+| 0.8453        | 1.4758 | 100  | 0.9692          |
+| 0.738         | 1.7732 | 120  | 0.9574          |
+| 0.7202        | 2.0595 | 140  | 0.9543          |
+| 0.7281        | 2.3569 | 160  | 0.9545          |
+| 0.5788        | 2.6543 | 180  | 0.9579          |
+| 0.6853        | 2.9517 | 200  | 0.9536          |
+
+
+### Framework versions
+
+- PEFT 0.18.0
+- Transformers 4.57.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.4.1
+- Tokenizers 0.22.1

trainer_state.json

@@ -0,0 +1,210 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.9536316990852356,
+  "best_model_checkpoint": "j05hr3d/SFT-Qwen2.5-Coder-3B_v6/checkpoint-200",
+  "epoch": 3.0,
+  "eval_steps": 20,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29739776951672864,
+      "grad_norm": 0.39164280891418457,
+      "learning_rate": 9.390862944162437e-05,
+      "loss": 1.064,
+      "step": 20
+    },
+    {
+      "epoch": 0.29739776951672864,
+      "eval_loss": 1.0908243656158447,
+      "eval_runtime": 12.8279,
+      "eval_samples_per_second": 4.521,
+      "eval_steps_per_second": 0.624,
+      "step": 20
+    },
+    {
+      "epoch": 0.5947955390334573,
+      "grad_norm": 0.49763497710227966,
+      "learning_rate": 8.375634517766498e-05,
+      "loss": 0.8857,
+      "step": 40
+    },
+    {
+      "epoch": 0.5947955390334573,
+      "eval_loss": 1.036130428314209,
+      "eval_runtime": 10.5527,
+      "eval_samples_per_second": 5.496,
+      "eval_steps_per_second": 0.758,
+      "step": 40
+    },
+    {
+      "epoch": 0.8921933085501859,
+      "grad_norm": 0.628839910030365,
+      "learning_rate": 7.360406091370558e-05,
+      "loss": 0.8355,
+      "step": 60
+    },
+    {
+      "epoch": 0.8921933085501859,
+      "eval_loss": 1.002919316291809,
+      "eval_runtime": 10.6087,
+      "eval_samples_per_second": 5.467,
+      "eval_steps_per_second": 0.754,
+      "step": 60
+    },
+    {
+      "epoch": 1.178438661710037,
+      "grad_norm": 0.5842138528823853,
+      "learning_rate": 6.34517766497462e-05,
+      "loss": 0.7792,
+      "step": 80
+    },
+    {
+      "epoch": 1.178438661710037,
+      "eval_loss": 0.9859979152679443,
+      "eval_runtime": 10.6347,
+      "eval_samples_per_second": 5.454,
+      "eval_steps_per_second": 0.752,
+      "step": 80
+    },
+    {
+      "epoch": 1.4758364312267658,
+      "grad_norm": 0.4571356475353241,
+      "learning_rate": 5.329949238578681e-05,
+      "loss": 0.8453,
+      "step": 100
+    },
+    {
+      "epoch": 1.4758364312267658,
+      "eval_loss": 0.969210147857666,
+      "eval_runtime": 10.6158,
+      "eval_samples_per_second": 5.464,
+      "eval_steps_per_second": 0.754,
+      "step": 100
+    },
+    {
+      "epoch": 1.7732342007434945,
+      "grad_norm": 0.33550629019737244,
+      "learning_rate": 4.3147208121827415e-05,
+      "loss": 0.738,
+      "step": 120
+    },
+    {
+      "epoch": 1.7732342007434945,
+      "eval_loss": 0.9574025869369507,
+      "eval_runtime": 10.5759,
+      "eval_samples_per_second": 5.484,
+      "eval_steps_per_second": 0.756,
+      "step": 120
+    },
+    {
+      "epoch": 2.059479553903346,
+      "grad_norm": 0.4646433889865875,
+      "learning_rate": 3.299492385786802e-05,
+      "loss": 0.7202,
+      "step": 140
+    },
+    {
+      "epoch": 2.059479553903346,
+      "eval_loss": 0.9542675018310547,
+      "eval_runtime": 10.5605,
+      "eval_samples_per_second": 5.492,
+      "eval_steps_per_second": 0.758,
+      "step": 140
+    },
+    {
+      "epoch": 2.356877323420074,
+      "grad_norm": 0.6946370601654053,
+      "learning_rate": 2.284263959390863e-05,
+      "loss": 0.7281,
+      "step": 160
+    },
+    {
+      "epoch": 2.356877323420074,
+      "eval_loss": 0.9544633030891418,
+      "eval_runtime": 10.5653,
+      "eval_samples_per_second": 5.49,
+      "eval_steps_per_second": 0.757,
+      "step": 160
+    },
+    {
+      "epoch": 2.654275092936803,
+      "grad_norm": 1.063151240348816,
+      "learning_rate": 1.2690355329949238e-05,
+      "loss": 0.5788,
+      "step": 180
+    },
+    {
+      "epoch": 2.654275092936803,
+      "eval_loss": 0.957865834236145,
+      "eval_runtime": 10.5723,
+      "eval_samples_per_second": 5.486,
+      "eval_steps_per_second": 0.757,
+      "step": 180
+    },
+    {
+      "epoch": 2.9516728624535316,
+      "grad_norm": 0.743322491645813,
+      "learning_rate": 2.5380710659898476e-06,
+      "loss": 0.6853,
+      "step": 200
+    },
+    {
+      "epoch": 2.9516728624535316,
+      "eval_loss": 0.9536316990852356,
+      "eval_runtime": 10.581,
+      "eval_samples_per_second": 5.482,
+      "eval_steps_per_second": 0.756,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "step": 204,
+      "total_flos": 3.158096666288947e+16,
+      "train_loss": 0.7847854272992003,
+      "train_runtime": 888.653,
+      "train_samples_per_second": 1.813,
+      "train_steps_per_second": 0.23
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9536316990852356,
+      "eval_runtime": 10.594,
+      "eval_samples_per_second": 5.475,
+      "eval_steps_per_second": 0.755,
+      "step": 204
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 204,
+  "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": 3.158096666288947e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}