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: qwen_s1ablation_length_filter_9k
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # qwen_s1ablation_length_filter_9k
 
-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/s1_ablation_length_filtering_1k dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.857142857142857,
+    "total_flos": 3.216871361662157e+16,
+    "train_loss": 0.6732408781846364,
+    "train_runtime": 2086.5899,
+    "train_samples_per_second": 1.436,
+    "train_steps_per_second": 0.014
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.857142857142857,
+    "total_flos": 3.216871361662157e+16,
+    "train_loss": 0.6732408781846364,
+    "train_runtime": 2086.5899,
+    "train_samples_per_second": 1.436,
+    "train_steps_per_second": 0.014
+}

trainer_state.json

@@ -0,0 +1,252 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.857142857142857,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 6.69879021328062,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.9254,
+      "step": 1
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 6.812172498992197,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.9124,
+      "step": 2
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 6.1968107570576025,
+      "learning_rate": 1e-05,
+      "loss": 0.9139,
+      "step": 3
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 3.031347956869276,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.8186,
+      "step": 4
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 4.799064885103958,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.8296,
+      "step": 5
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 4.947222347193089,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.8429,
+      "step": 6
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 4.83331880845543,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 0.7157,
+      "step": 7
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 4.315493531376812,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.7624,
+      "step": 8
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 2.685844169348072,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.7511,
+      "step": 9
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.877732979420426,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.7106,
+      "step": 10
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 1.9137283504219358,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.6701,
+      "step": 11
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.5308954847056906,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.6419,
+      "step": 12
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 1.0381488329849287,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 0.6448,
+      "step": 13
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.9263814321062724,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.6187,
+      "step": 14
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.9521318815963339,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.6347,
+      "step": 15
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 1.0095244156682712,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.6207,
+      "step": 16
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.756753602989596,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 0.6225,
+      "step": 17
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.7518844551349931,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.5996,
+      "step": 18
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.7158969770648573,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.5921,
+      "step": 19
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.7158289257407585,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.6172,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6721220687452227,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.6017,
+      "step": 21
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.6116023499140204,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.5649,
+      "step": 22
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.6299802169587033,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 0.5626,
+      "step": 23
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.5851068507732032,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.5914,
+      "step": 24
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.5089300842985366,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.5802,
+      "step": 25
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.5541097534961649,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.5819,
+      "step": 26
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.5528628712955269,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.5562,
+      "step": 27
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.537108464148477,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.5873,
+      "step": 28
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.4900868436883477,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.5579,
+      "step": 29
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.4909822824804804,
+      "learning_rate": 0.0,
+      "loss": 0.5682,
+      "step": 30
+    },
+    {
+      "epoch": 2.857142857142857,
+      "step": 30,
+      "total_flos": 3.216871361662157e+16,
+      "train_loss": 0.6732408781846364,
+      "train_runtime": 2086.5899,
+      "train_samples_per_second": 1.436,
+      "train_steps_per_second": 0.014
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.216871361662157e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}