End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: hp_ablations_mistral_epoch1_dcftv1.2
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hp_ablations_mistral_epoch1_dcftv1.2
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0715
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9976343359242987,
+    "eval_loss": 0.07151415199041367,
+    "eval_runtime": 378.6365,
+    "eval_samples_per_second": 26.318,
+    "eval_steps_per_second": 0.412,
+    "total_flos": 617879363911680.0,
+    "train_loss": 0.6010491040340931,
+    "train_runtime": 20904.0457,
+    "train_samples_per_second": 9.057,
+    "train_steps_per_second": 0.018
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9976343359242987,
+    "eval_loss": 0.07151415199041367,
+    "eval_runtime": 378.6365,
+    "eval_samples_per_second": 26.318,
+    "eval_steps_per_second": 0.412
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9976343359242987,
+    "total_flos": 617879363911680.0,
+    "train_loss": 0.6010491040340931,
+    "train_runtime": 20904.0457,
+    "train_samples_per_second": 9.057,
+    "train_steps_per_second": 0.018
+}

trainer_state.json

@@ -0,0 +1,302 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9976343359242987,
+  "eval_steps": 500,
+  "global_step": 369,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.027036160865157147,
+      "grad_norm": 3.4784094928764935,
+      "learning_rate": 5e-06,
+      "loss": 0.8618,
+      "step": 10
+    },
+    {
+      "epoch": 0.054072321730314295,
+      "grad_norm": 2.388779710314854,
+      "learning_rate": 5e-06,
+      "loss": 0.6871,
+      "step": 20
+    },
+    {
+      "epoch": 0.08110848259547145,
+      "grad_norm": 2.8448643085609833,
+      "learning_rate": 5e-06,
+      "loss": 0.6493,
+      "step": 30
+    },
+    {
+      "epoch": 0.10814464346062859,
+      "grad_norm": 2.009530503518872,
+      "learning_rate": 5e-06,
+      "loss": 0.6366,
+      "step": 40
+    },
+    {
+      "epoch": 0.13518080432578575,
+      "grad_norm": 1.7430484878994352,
+      "learning_rate": 5e-06,
+      "loss": 0.6208,
+      "step": 50
+    },
+    {
+      "epoch": 0.1622169651909429,
+      "grad_norm": 2.723767071364954,
+      "learning_rate": 5e-06,
+      "loss": 0.6159,
+      "step": 60
+    },
+    {
+      "epoch": 0.18925312605610004,
+      "grad_norm": 1.8832010489539412,
+      "learning_rate": 5e-06,
+      "loss": 0.6136,
+      "step": 70
+    },
+    {
+      "epoch": 0.21628928692125718,
+      "grad_norm": 1.974120312681986,
+      "learning_rate": 5e-06,
+      "loss": 0.6041,
+      "step": 80
+    },
+    {
+      "epoch": 0.24332544778641432,
+      "grad_norm": 1.8595623349930193,
+      "learning_rate": 5e-06,
+      "loss": 0.6011,
+      "step": 90
+    },
+    {
+      "epoch": 0.2703616086515715,
+      "grad_norm": 2.255803847585017,
+      "learning_rate": 5e-06,
+      "loss": 0.6054,
+      "step": 100
+    },
+    {
+      "epoch": 0.29739776951672864,
+      "grad_norm": 1.6500621830470217,
+      "learning_rate": 5e-06,
+      "loss": 0.601,
+      "step": 110
+    },
+    {
+      "epoch": 0.3244339303818858,
+      "grad_norm": 1.3954974486021101,
+      "learning_rate": 5e-06,
+      "loss": 0.5952,
+      "step": 120
+    },
+    {
+      "epoch": 0.3514700912470429,
+      "grad_norm": 1.4731050833701078,
+      "learning_rate": 5e-06,
+      "loss": 0.5968,
+      "step": 130
+    },
+    {
+      "epoch": 0.37850625211220007,
+      "grad_norm": 2.621850441642734,
+      "learning_rate": 5e-06,
+      "loss": 0.5981,
+      "step": 140
+    },
+    {
+      "epoch": 0.4055424129773572,
+      "grad_norm": 3.1610278131950165,
+      "learning_rate": 5e-06,
+      "loss": 0.5914,
+      "step": 150
+    },
+    {
+      "epoch": 0.43257857384251436,
+      "grad_norm": 2.6773053485949574,
+      "learning_rate": 5e-06,
+      "loss": 0.5916,
+      "step": 160
+    },
+    {
+      "epoch": 0.4596147347076715,
+      "grad_norm": 2.6324269251247463,
+      "learning_rate": 5e-06,
+      "loss": 0.5908,
+      "step": 170
+    },
+    {
+      "epoch": 0.48665089557282865,
+      "grad_norm": 1.7739498794233857,
+      "learning_rate": 5e-06,
+      "loss": 0.5898,
+      "step": 180
+    },
+    {
+      "epoch": 0.5136870564379858,
+      "grad_norm": 2.1873587079817116,
+      "learning_rate": 5e-06,
+      "loss": 0.5865,
+      "step": 190
+    },
+    {
+      "epoch": 0.540723217303143,
+      "grad_norm": 2.3678283018771817,
+      "learning_rate": 5e-06,
+      "loss": 0.5844,
+      "step": 200
+    },
+    {
+      "epoch": 0.5677593781683001,
+      "grad_norm": 1.7202822631450192,
+      "learning_rate": 5e-06,
+      "loss": 0.5868,
+      "step": 210
+    },
+    {
+      "epoch": 0.5947955390334573,
+      "grad_norm": 2.010532321211627,
+      "learning_rate": 5e-06,
+      "loss": 0.5824,
+      "step": 220
+    },
+    {
+      "epoch": 0.6218316998986144,
+      "grad_norm": 1.5092451807309508,
+      "learning_rate": 5e-06,
+      "loss": 0.5845,
+      "step": 230
+    },
+    {
+      "epoch": 0.6488678607637716,
+      "grad_norm": 1.3402777424581782,
+      "learning_rate": 5e-06,
+      "loss": 0.581,
+      "step": 240
+    },
+    {
+      "epoch": 0.6759040216289287,
+      "grad_norm": 2.122509251204482,
+      "learning_rate": 5e-06,
+      "loss": 0.5749,
+      "step": 250
+    },
+    {
+      "epoch": 0.7029401824940859,
+      "grad_norm": 2.1557415576448675,
+      "learning_rate": 5e-06,
+      "loss": 0.5791,
+      "step": 260
+    },
+    {
+      "epoch": 0.729976343359243,
+      "grad_norm": 2.0280150214024815,
+      "learning_rate": 5e-06,
+      "loss": 0.582,
+      "step": 270
+    },
+    {
+      "epoch": 0.7570125042244001,
+      "grad_norm": 1.4201449456429993,
+      "learning_rate": 5e-06,
+      "loss": 0.5757,
+      "step": 280
+    },
+    {
+      "epoch": 0.7840486650895573,
+      "grad_norm": 1.9345087558176988,
+      "learning_rate": 5e-06,
+      "loss": 0.5754,
+      "step": 290
+    },
+    {
+      "epoch": 0.8110848259547144,
+      "grad_norm": 1.4797191257671278,
+      "learning_rate": 5e-06,
+      "loss": 0.5759,
+      "step": 300
+    },
+    {
+      "epoch": 0.8381209868198716,
+      "grad_norm": 1.9492470809520732,
+      "learning_rate": 5e-06,
+      "loss": 0.5736,
+      "step": 310
+    },
+    {
+      "epoch": 0.8651571476850287,
+      "grad_norm": 1.3763506210486918,
+      "learning_rate": 5e-06,
+      "loss": 0.5721,
+      "step": 320
+    },
+    {
+      "epoch": 0.8921933085501859,
+      "grad_norm": 1.543300257199387,
+      "learning_rate": 5e-06,
+      "loss": 0.5733,
+      "step": 330
+    },
+    {
+      "epoch": 0.919229469415343,
+      "grad_norm": 1.4892346924091908,
+      "learning_rate": 5e-06,
+      "loss": 0.5801,
+      "step": 340
+    },
+    {
+      "epoch": 0.9462656302805001,
+      "grad_norm": 1.7524350925753447,
+      "learning_rate": 5e-06,
+      "loss": 0.5725,
+      "step": 350
+    },
+    {
+      "epoch": 0.9733017911456573,
+      "grad_norm": 1.5210562130955052,
+      "learning_rate": 5e-06,
+      "loss": 0.5722,
+      "step": 360
+    },
+    {
+      "epoch": 0.9976343359242987,
+      "eval_loss": 0.07151415199041367,
+      "eval_runtime": 375.0467,
+      "eval_samples_per_second": 26.57,
+      "eval_steps_per_second": 0.416,
+      "step": 369
+    },
+    {
+      "epoch": 0.9976343359242987,
+      "step": 369,
+      "total_flos": 617879363911680.0,
+      "train_loss": 0.6010491040340931,
+      "train_runtime": 20904.0457,
+      "train_samples_per_second": 9.057,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 369,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 617879363911680.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}