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: 316_globalbatchsize64_lr1e5_epochs7
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 316_globalbatchsize64_lr1e5_epochs7
 
-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/openthoughts_316 dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 4.553463888976282e+16,
+    "train_loss": 0.6423646134989602,
+    "train_runtime": 2917.9198,
+    "train_samples_per_second": 0.758,
+    "train_steps_per_second": 0.012
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 4.553463888976282e+16,
+    "train_loss": 0.6423646134989602,
+    "train_runtime": 2917.9198,
+    "train_samples_per_second": 0.758,
+    "train_steps_per_second": 0.012
+}

trainer_state.json

@@ -0,0 +1,287 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 35,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.582358906147192,
+      "learning_rate": 2.5e-06,
+      "loss": 0.832,
+      "step": 1
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.007640746275026,
+      "learning_rate": 5e-06,
+      "loss": 0.8909,
+      "step": 2
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.714795332116958,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8979,
+      "step": 3
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.265716037342555,
+      "learning_rate": 1e-05,
+      "loss": 0.8648,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.085029182097334,
+      "learning_rate": 9.974346616959476e-06,
+      "loss": 0.7839,
+      "step": 5
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 5.651803536405543,
+      "learning_rate": 9.897649706262474e-06,
+      "loss": 0.8144,
+      "step": 6
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 7.350623039861967,
+      "learning_rate": 9.770696282000245e-06,
+      "loss": 0.8331,
+      "step": 7
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 7.604729650135797,
+      "learning_rate": 9.594789058101154e-06,
+      "loss": 0.8294,
+      "step": 8
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 6.2283021470847455,
+      "learning_rate": 9.371733080722911e-06,
+      "loss": 0.8138,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.6961381554678794,
+      "learning_rate": 9.103817206036383e-06,
+      "loss": 0.7548,
+      "step": 10
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.1721850533837705,
+      "learning_rate": 8.793790613463956e-06,
+      "loss": 0.7297,
+      "step": 11
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.1393892089477733,
+      "learning_rate": 8.444834595378434e-06,
+      "loss": 0.6719,
+      "step": 12
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.4179199525638273,
+      "learning_rate": 8.060529912738316e-06,
+      "loss": 0.6487,
+      "step": 13
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.4009912746793316,
+      "learning_rate": 7.644820051634813e-06,
+      "loss": 0.6703,
+      "step": 14
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0272214968725972,
+      "learning_rate": 7.201970757788172e-06,
+      "loss": 0.6456,
+      "step": 15
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.9562542078090331,
+      "learning_rate": 6.736526264224101e-06,
+      "loss": 0.5806,
+      "step": 16
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.9062032042356861,
+      "learning_rate": 6.2532626612936035e-06,
+      "loss": 0.6585,
+      "step": 17
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.7271473588203766,
+      "learning_rate": 5.757138887522884e-06,
+      "loss": 0.5956,
+      "step": 18
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.7742246369208975,
+      "learning_rate": 5.253245844193564e-06,
+      "loss": 0.5971,
+      "step": 19
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7164132908170959,
+      "learning_rate": 4.746754155806437e-06,
+      "loss": 0.5276,
+      "step": 20
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 0.5499030834011936,
+      "learning_rate": 4.2428611124771184e-06,
+      "loss": 0.5727,
+      "step": 21
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.5542153239024126,
+      "learning_rate": 3.7467373387063973e-06,
+      "loss": 0.5251,
+      "step": 22
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 0.6029015493144163,
+      "learning_rate": 3.2634737357758994e-06,
+      "loss": 0.5381,
+      "step": 23
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.682283388561948,
+      "learning_rate": 2.7980292422118282e-06,
+      "loss": 0.548,
+      "step": 24
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5141680917899011,
+      "learning_rate": 2.3551799483651894e-06,
+      "loss": 0.5366,
+      "step": 25
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.5052161464784082,
+      "learning_rate": 1.9394700872616856e-06,
+      "loss": 0.5633,
+      "step": 26
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 0.4888663290970337,
+      "learning_rate": 1.555165404621567e-06,
+      "loss": 0.5344,
+      "step": 27
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.48645872089664294,
+      "learning_rate": 1.2062093865360458e-06,
+      "loss": 0.5252,
+      "step": 28
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.4608389733467722,
+      "learning_rate": 8.961827939636198e-07,
+      "loss": 0.4861,
+      "step": 29
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.41306710261326274,
+      "learning_rate": 6.282669192770896e-07,
+      "loss": 0.4784,
+      "step": 30
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 0.4177769738137263,
+      "learning_rate": 4.05210941898847e-07,
+      "loss": 0.5251,
+      "step": 31
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.4447808771104787,
+      "learning_rate": 2.2930371799975593e-07,
+      "loss": 0.5024,
+      "step": 32
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 0.42694981358254674,
+      "learning_rate": 1.0235029373752758e-07,
+      "loss": 0.4919,
+      "step": 33
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.41995366862980577,
+      "learning_rate": 2.5653383040524228e-08,
+      "loss": 0.5287,
+      "step": 34
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.3932952185861738,
+      "learning_rate": 0.0,
+      "loss": 0.486,
+      "step": 35
+    },
+    {
+      "epoch": 7.0,
+      "step": 35,
+      "total_flos": 4.553463888976282e+16,
+      "train_loss": 0.6423646134989602,
+      "train_runtime": 2917.9198,
+      "train_samples_per_second": 0.758,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 35,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 4.553463888976282e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}