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: deepspeed_no_offload
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # deepspeed_no_offload
 
-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/instruction_filtering_scale_up_code_base_gemini_length_1K dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.875,
+    "total_flos": 29051356905472.0,
+    "train_loss": 0.8214895228544871,
+    "train_runtime": 980.7947,
+    "train_samples_per_second": 3.059,
+    "train_steps_per_second": 0.031
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.875,
+    "total_flos": 29051356905472.0,
+    "train_loss": 0.8214895228544871,
+    "train_runtime": 980.7947,
+    "train_samples_per_second": 3.059,
+    "train_steps_per_second": 0.031
+}

trainer_state.json

@@ -0,0 +1,252 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.875,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09375,
+      "grad_norm": 5.848947847974621,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0596,
+      "step": 1
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 5.629233229853796,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0409,
+      "step": 2
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 5.124287513702501,
+      "learning_rate": 1e-05,
+      "loss": 1.0219,
+      "step": 3
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 2.172807623744435,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.8987,
+      "step": 4
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 3.805373725353558,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.9111,
+      "step": 5
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 3.612298678500183,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.91,
+      "step": 6
+    },
+    {
+      "epoch": 0.65625,
+      "grad_norm": 3.071268661475005,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 0.8984,
+      "step": 7
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.561115074733964,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.897,
+      "step": 8
+    },
+    {
+      "epoch": 0.84375,
+      "grad_norm": 1.9788120260785862,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.8387,
+      "step": 9
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 1.3824566280670403,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.8219,
+      "step": 10
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 2.545630937144125,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 1.3902,
+      "step": 11
+    },
+    {
+      "epoch": 1.15625,
+      "grad_norm": 1.2097063430470212,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.731,
+      "step": 12
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.9935869176448624,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 0.7711,
+      "step": 13
+    },
+    {
+      "epoch": 1.34375,
+      "grad_norm": 0.896186899957696,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.7208,
+      "step": 14
+    },
+    {
+      "epoch": 1.4375,
+      "grad_norm": 0.8731827550593875,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.768,
+      "step": 15
+    },
+    {
+      "epoch": 1.53125,
+      "grad_norm": 0.9568145439323135,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.7986,
+      "step": 16
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.8194084736070346,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 0.6938,
+      "step": 17
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 0.6317375108380635,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.7286,
+      "step": 18
+    },
+    {
+      "epoch": 1.8125,
+      "grad_norm": 0.6393803017408335,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.7368,
+      "step": 19
+    },
+    {
+      "epoch": 1.90625,
+      "grad_norm": 0.6680807129989409,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.6755,
+      "step": 20
+    },
+    {
+      "epoch": 2.03125,
+      "grad_norm": 1.1768866366834774,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 1.192,
+      "step": 21
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.61326810252783,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.6694,
+      "step": 22
+    },
+    {
+      "epoch": 2.21875,
+      "grad_norm": 0.5698711147962973,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 0.6785,
+      "step": 23
+    },
+    {
+      "epoch": 2.3125,
+      "grad_norm": 0.5632280530521516,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.7031,
+      "step": 24
+    },
+    {
+      "epoch": 2.40625,
+      "grad_norm": 0.5177730720085312,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.6561,
+      "step": 25
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.4692665828108187,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.6628,
+      "step": 26
+    },
+    {
+      "epoch": 2.59375,
+      "grad_norm": 0.505366495274329,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.7112,
+      "step": 27
+    },
+    {
+      "epoch": 2.6875,
+      "grad_norm": 0.4709483095180629,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.6845,
+      "step": 28
+    },
+    {
+      "epoch": 2.78125,
+      "grad_norm": 0.4473168765960649,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.6777,
+      "step": 29
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.516034185354372,
+      "learning_rate": 0.0,
+      "loss": 0.6966,
+      "step": 30
+    },
+    {
+      "epoch": 2.875,
+      "step": 30,
+      "total_flos": 29051356905472.0,
+      "train_loss": 0.8214895228544871,
+      "train_runtime": 980.7947,
+      "train_samples_per_second": 3.059,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 30,
+  "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": 29051356905472.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}