Model save

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jhinpan-university-of-michigan/huggingface/runs/84s06xri) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jhinpan-university-of-michigan/huggingface/runs/sol4t6ql) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 76916824473600.0,
-    "train_loss": 0.8026482480517506,
-    "train_runtime": 2173.7189,
+    "train_loss": 0.8026284212191429,
+    "train_runtime": 2177.557,
     "train_samples": 16610,
-    "train_samples_per_second": 9.941,
+    "train_samples_per_second": 9.924,
     "train_steps_per_second": 0.078
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8238e18446441e1c8729ed0dfbfeb7cd7454b7c4777401e82359c2a24989724e
+oid sha256:e56051cf3f92d58b2919c239ff31fdfc8494d92fd58c261b28707031c5b58fc6
 size 3087467144

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 76916824473600.0,
-    "train_loss": 0.8026482480517506,
-    "train_runtime": 2173.7189,
+    "train_loss": 0.8026284212191429,
+    "train_runtime": 2177.557,
     "train_samples": 16610,
-    "train_samples_per_second": 9.941,
+    "train_samples_per_second": 9.924,
     "train_steps_per_second": 0.078
 }

trainer_state.json

@@ -10,250 +10,250 @@
   "log_history": [
     {
       "epoch": 0.029585798816568046,
-      "grad_norm": 2.3431173127732823,
+      "grad_norm": 2.3432942789122944,
       "learning_rate": 5.882352941176471e-06,
       "loss": 1.0993,
       "step": 5
     },
     {
       "epoch": 0.05917159763313609,
-      "grad_norm": 1.6357344843753208,
+      "grad_norm": 1.632593500466657,
       "learning_rate": 1.1764705882352942e-05,
-      "loss": 1.0402,
+      "loss": 1.0401,
       "step": 10
     },
     {
       "epoch": 0.08875739644970414,
-      "grad_norm": 0.8981578326750542,
+      "grad_norm": 0.8942322427235943,
       "learning_rate": 1.7647058823529414e-05,
       "loss": 0.9534,
       "step": 15
     },
     {
       "epoch": 0.11834319526627218,
-      "grad_norm": 0.6112758529003858,
+      "grad_norm": 0.6126896287772365,
       "learning_rate": 1.9980782984658682e-05,
-      "loss": 0.8922,
+      "loss": 0.8923,
       "step": 20
     },
     {
       "epoch": 0.14792899408284024,
-      "grad_norm": 0.5474374534751283,
+      "grad_norm": 0.5454130318595319,
       "learning_rate": 1.9863613034027224e-05,
       "loss": 0.8551,
       "step": 25
     },
     {
       "epoch": 0.17751479289940827,
-      "grad_norm": 0.43286435198096246,
+      "grad_norm": 0.43357600780023264,
       "learning_rate": 1.9641197940012136e-05,
       "loss": 0.8282,
       "step": 30
     },
     {
       "epoch": 0.20710059171597633,
-      "grad_norm": 0.38307029714187024,
+      "grad_norm": 0.3842410711336726,
       "learning_rate": 1.9315910880512792e-05,
       "loss": 0.8229,
       "step": 35
     },
     {
       "epoch": 0.23668639053254437,
-      "grad_norm": 0.4064008859336551,
+      "grad_norm": 0.40636484130587147,
       "learning_rate": 1.8891222681391853e-05,
-      "loss": 0.8224,
+      "loss": 0.8223,
       "step": 40
     },
     {
       "epoch": 0.26627218934911245,
-      "grad_norm": 0.3531499460335522,
+      "grad_norm": 0.35252971874465805,
       "learning_rate": 1.8371664782625287e-05,
       "loss": 0.8073,
       "step": 45
     },
     {
       "epoch": 0.2958579881656805,
-      "grad_norm": 0.3432888241812474,
+      "grad_norm": 0.3428348239010054,
       "learning_rate": 1.7762780887657576e-05,
       "loss": 0.7977,
       "step": 50
     },
     {
       "epoch": 0.3254437869822485,
-      "grad_norm": 0.38256763842685093,
+      "grad_norm": 0.38285428364946616,
       "learning_rate": 1.7071067811865477e-05,
       "loss": 0.7877,
       "step": 55
     },
     {
       "epoch": 0.35502958579881655,
-      "grad_norm": 0.3846624566037706,
+      "grad_norm": 0.3813919306318996,
       "learning_rate": 1.6303906161279554e-05,
       "loss": 0.7981,
       "step": 60
     },
     {
       "epoch": 0.38461538461538464,
-      "grad_norm": 0.3492784882724837,
+      "grad_norm": 0.3510587014306315,
       "learning_rate": 1.5469481581224274e-05,
-      "loss": 0.7721,
+      "loss": 0.7722,
       "step": 65
     },
     {
       "epoch": 0.41420118343195267,
-      "grad_norm": 0.34933839481384543,
+      "grad_norm": 0.34990321470097296,
       "learning_rate": 1.4576697415156818e-05,
-      "loss": 0.7741,
+      "loss": 0.774,
       "step": 70
     },
     {
       "epoch": 0.4437869822485207,
-      "grad_norm": 0.3438131662172999,
+      "grad_norm": 0.34429088444308475,
       "learning_rate": 1.3635079705638298e-05,
       "loss": 0.7852,
       "step": 75
     },
     {
       "epoch": 0.47337278106508873,
-      "grad_norm": 0.35709135697153294,
+      "grad_norm": 0.36020582680360763,
       "learning_rate": 1.2654675551080724e-05,
       "loss": 0.7666,
       "step": 80
     },
     {
       "epoch": 0.5029585798816568,
-      "grad_norm": 0.376932703008634,
+      "grad_norm": 0.37727270566714344,
       "learning_rate": 1.164594590280734e-05,
       "loss": 0.7706,
       "step": 85
     },
     {
       "epoch": 0.5325443786982249,
-      "grad_norm": 0.36493154551683576,
+      "grad_norm": 0.3669254574454686,
       "learning_rate": 1.0619653946285948e-05,
       "loss": 0.77,
       "step": 90
     },
     {
       "epoch": 0.5621301775147929,
-      "grad_norm": 0.36828396438195643,
+      "grad_norm": 0.3773759399081079,
       "learning_rate": 9.586750257511868e-06,
       "loss": 0.7771,
       "step": 95
     },
     {
       "epoch": 0.591715976331361,
-      "grad_norm": 0.34523064327510505,
+      "grad_norm": 0.34501156726704085,
       "learning_rate": 8.558255959926533e-06,
       "loss": 0.753,
       "step": 100
     },
     {
       "epoch": 0.591715976331361,
-      "eval_loss": 0.7880551218986511,
-      "eval_runtime": 3.4088,
-      "eval_samples_per_second": 37.549,
-      "eval_steps_per_second": 1.173,
+      "eval_loss": 0.7881231307983398,
+      "eval_runtime": 3.4153,
+      "eval_samples_per_second": 37.479,
+      "eval_steps_per_second": 1.171,
       "step": 100
     },
     {
       "epoch": 0.621301775147929,
-      "grad_norm": 0.3412506327233745,
+      "grad_norm": 0.3411341726663563,
       "learning_rate": 7.545145128592009e-06,
-      "loss": 0.757,
+      "loss": 0.7569,
       "step": 105
     },
     {
       "epoch": 0.650887573964497,
-      "grad_norm": 0.352876905849451,
+      "grad_norm": 0.3556780170027034,
       "learning_rate": 6.558227696373617e-06,
       "loss": 0.7681,
       "step": 110
     },
     {
       "epoch": 0.6804733727810651,
-      "grad_norm": 0.31451209289570714,
+      "grad_norm": 0.3147767018346297,
       "learning_rate": 5.608034111526298e-06,
       "loss": 0.7623,
       "step": 115
     },
     {
       "epoch": 0.7100591715976331,
-      "grad_norm": 0.3026500048757784,
+      "grad_norm": 0.3018086447379154,
       "learning_rate": 4.704702977392914e-06,
-      "loss": 0.7514,
+      "loss": 0.7513,
       "step": 120
     },
     {
       "epoch": 0.7396449704142012,
-      "grad_norm": 0.35293898377100963,
+      "grad_norm": 0.35168113902794573,
       "learning_rate": 3.857872873103322e-06,
       "loss": 0.7538,
       "step": 125
     },
     {
       "epoch": 0.7692307692307693,
-      "grad_norm": 0.3206136015508239,
+      "grad_norm": 0.3178814791481331,
       "learning_rate": 3.0765795095517026e-06,
       "loss": 0.7555,
       "step": 130
     },
     {
       "epoch": 0.7988165680473372,
-      "grad_norm": 0.32830065829139476,
+      "grad_norm": 0.3287145915766805,
       "learning_rate": 2.369159318001937e-06,
       "loss": 0.7584,
       "step": 135
     },
     {
       "epoch": 0.8284023668639053,
-      "grad_norm": 0.3029891286321494,
+      "grad_norm": 0.30415025271489804,
       "learning_rate": 1.743160500034443e-06,
       "loss": 0.7498,
       "step": 140
     },
     {
       "epoch": 0.8579881656804734,
-      "grad_norm": 0.31726665858640396,
+      "grad_norm": 0.3210204614526349,
       "learning_rate": 1.2052624879351105e-06,
       "loss": 0.7566,
       "step": 145
     },
     {
       "epoch": 0.8875739644970414,
-      "grad_norm": 0.2996674732689918,
+      "grad_norm": 0.3002171922384317,
       "learning_rate": 7.612046748871327e-07,
       "loss": 0.7666,
       "step": 150
     },
     {
       "epoch": 0.9171597633136095,
-      "grad_norm": 0.3019679956832725,
+      "grad_norm": 0.3014998795592546,
       "learning_rate": 4.1572517541747294e-07,
       "loss": 0.7613,
       "step": 155
     },
     {
       "epoch": 0.9467455621301775,
-      "grad_norm": 0.2906670362783664,
+      "grad_norm": 0.2906058726578308,
       "learning_rate": 1.7251026952640583e-07,
       "loss": 0.7607,
       "step": 160
     },
     {
       "epoch": 0.9763313609467456,
-      "grad_norm": 0.28084999928439486,
+      "grad_norm": 0.28057495728367504,
       "learning_rate": 3.4155069933301535e-08,
-      "loss": 0.7446,
+      "loss": 0.7445,
       "step": 165
     },
     {
       "epoch": 1.0,
       "step": 169,
       "total_flos": 76916824473600.0,
-      "train_loss": 0.8026482480517506,
-      "train_runtime": 2173.7189,
-      "train_samples_per_second": 9.941,
+      "train_loss": 0.8026284212191429,
+      "train_runtime": 2177.557,
+      "train_samples_per_second": 9.924,
       "train_steps_per_second": 0.078
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9874d727600073f3eaca54c08c97eda39589ecfc200cecb67bb84155c4e871
+oid sha256:d78e98125b6d82337defd7d4533d46f1829aa4e293679d13ad68aaf24d1b9c81
 size 7352