End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: ds_no_offload_liger_packing_torchcompile
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ds_no_offload_liger_packing_torchcompile
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/wikipedia_seed_science dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6.177445717318042e+16,
+    "train_loss": 1.029662208424674,
+    "train_runtime": 1352.1307,
+    "train_samples_per_second": 1.276,
+    "train_steps_per_second": 0.013
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6.177445717318042e+16,
+    "train_loss": 1.029662208424674,
+    "train_runtime": 1352.1307,
+    "train_samples_per_second": 1.276,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 8.517669765654716,
+      "learning_rate": 5e-06,
+      "loss": 1.2823,
+      "step": 1
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 9.018825165807502,
+      "learning_rate": 1e-05,
+      "loss": 1.3191,
+      "step": 2
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.196050443485397,
+      "learning_rate": 9.903926402016153e-06,
+      "loss": 1.2058,
+      "step": 3
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 3.0228679865058354,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 1.1293,
+      "step": 4
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 6.119739448069098,
+      "learning_rate": 9.157348061512728e-06,
+      "loss": 1.144,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.666382250190595,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 1.0848,
+      "step": 6
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 6.842061565934544,
+      "learning_rate": 7.777851165098012e-06,
+      "loss": 1.0694,
+      "step": 7
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 4.957214312741355,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 1.0375,
+      "step": 8
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.209745641197134,
+      "learning_rate": 5.975451610080643e-06,
+      "loss": 1.0121,
+      "step": 9
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.0514807282761196,
+      "learning_rate": 5e-06,
+      "loss": 0.9652,
+      "step": 10
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 2.187925473273816,
+      "learning_rate": 4.02454838991936e-06,
+      "loss": 0.9329,
+      "step": 11
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0015260589023445,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.9326,
+      "step": 12
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 1.6357816010052606,
+      "learning_rate": 2.2221488349019903e-06,
+      "loss": 0.9088,
+      "step": 13
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 1.3115476552755818,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.8942,
+      "step": 14
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.1366506975077333,
+      "learning_rate": 8.426519384872733e-07,
+      "loss": 0.9139,
+      "step": 15
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.9087945975282256,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.905,
+      "step": 16
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.7708865631810711,
+      "learning_rate": 9.607359798384785e-08,
+      "loss": 0.9043,
+      "step": 17
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7019414829061189,
+      "learning_rate": 0.0,
+      "loss": 0.8928,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "step": 18,
+      "total_flos": 6.177445717318042e+16,
+      "train_loss": 1.029662208424674,
+      "train_runtime": 1352.1307,
+      "train_samples_per_second": 1.276,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.177445717318042e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}