Training in progress, step 500, checkpoint

last-checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525eac99ad96fc44058191ab19adc5993ebaea58b8e0178702747f1ee3435202
+oid sha256:a4570838371cb46cb81aa6e4e93e439795cf68c0acdb027e6d242243ef305391
 size 4962001760

last-checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:558c4922ee8c74243d0fdb31e3e04330963270eac20e7e5f27843b699e5bb2a2
+oid sha256:1d816528d00db7afcf13755816f471a57e2401601af1e498b925651fb1ee7141
 size 4915916160

last-checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56220ae9514cffaa65f5e69f741b689c6b09c909e431ece359e6cc8fc172facf
+oid sha256:9e2a7109a89481a14c23ebcca39f764b77662153e1d11566a1997fcbb214fdec
 size 4999819336

last-checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b75675ac64f9f371e8692d260bb19c22ec999a3cdfd5bed397548ae96194d4
+oid sha256:c4b9c1b25cb5cc33bd227513645df9037e53f4f31852a7141c5f1585c5401666
 size 1623221024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbbf775bc02f0e5313eea63ceadf33473d5eb33db11880946d7f8cd32301931
+oid sha256:006f3cb0dd1a2817bf4e23a383a26d52ed1f7f87a0ddb412aec4aae524addbbe
 size 13053963

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a163c08920e0f5521e8b4bad62b9d358b8cbc6506edd88b7096a6ffc2a7c242d
+oid sha256:a8b9684a001ced786cf3f8d180da14cc75fa2707f771fb8db8a2f3987616d58a
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876bd3e9fc68db1c95fed624955b5fd3f484c7a9299d86e57f3ba1ddf3348179
+oid sha256:69a7fd708494878bd9a17192c05a815384b2db4098489cd7778c553943417ba7
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517ac8bafc12147371b154cd689f10e05f9ee0f90b1a1d98261bc402b3794d28
+oid sha256:5f6f6314518ebe461b62a277be61b06e05bed27aea542e4ae2bffb060e73689a
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf5db3a4eb888f369dfe32f926286928204680ca9125437e1b7c7b3f270ab15
+oid sha256:0d6a9499db1eadd54ce72d5506ca43e60264cf1a33ebf777e4ed3931ed1a03b9
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59728ce06aff590492cee7a3ae474ff2766e75b2b0d12b0ecb1e0ed3c034d59
+oid sha256:e4e82eac1af25e6d36636846ff6b561653dba1263d790f10f82c5fa93bfeb01a
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c2193cb033eebca6c12e4a1e29534cc18579a6cad159bde288623281c5c35d2
+oid sha256:41aa0f60e2dc0839912ac9319700da038b4ead806802304d22298e9dd3372ae9
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed1143ef96cc6fb0d682bd8e4f30c0e8393b47d3bfc04f20f3b76342f03f9600
+oid sha256:3586402bd40d50079663ce2ab2f6725fc21b6aa67d9ba6b8985080086eb3fd05
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057a179eb770c90e474fec0e25f409212d61bb896d2da1bbccb971884ff21913
+oid sha256:8b3318c70326f3b79256c222c497e48e741ec33cc9f1c47dd67359e1fee68294
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c002680d92a128e78b90abe033ccb635fd42c0f7b5d06a2d995a5f9b60d18627
+oid sha256:504c0ac187a5cb09c6c830e073a49c85f9ed8f4f258d346199b3f76f0521e60a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.333333333333333,
+  "epoch": 6.666666666666667,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -491,6 +491,124 @@
       "loss": 0.4644,
       "rewards/chosen": 5.071358489990234,
       "step": 400
+    },
+    {
+      "epoch": 5.466666666666667,
+      "grad_norm": 48.0,
+      "kl": 55.76483154296875,
+      "learning_rate": 4.5466666666666666e-07,
+      "logits/chosen": 1760807936.0,
+      "logps/chosen": -1618.9923828125,
+      "loss": 0.5002,
+      "rewards/chosen": 5.545055770874024,
+      "step": 410
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 50.0,
+      "kl": 18.410531997680664,
+      "learning_rate": 4.413333333333333e-07,
+      "logits/chosen": 1736117544.672897,
+      "logits/rejected": 1708876583.6619718,
+      "logps/chosen": -1447.1404789719627,
+      "logps/rejected": -1516.6236795774648,
+      "loss": 0.3554,
+      "rewards/chosen": 5.60440890588493,
+      "rewards/margins": 6.6215995436077515,
+      "rewards/rejected": -1.0171906377228213,
+      "step": 420
+    },
+    {
+      "epoch": 5.733333333333333,
+      "grad_norm": 39.25,
+      "kl": 0.028980541974306107,
+      "learning_rate": 4.2799999999999997e-07,
+      "logits/rejected": 1704340684.8,
+      "logps/rejected": -1610.3271484375,
+      "loss": 0.269,
+      "rewards/rejected": -1.4840303421020509,
+      "step": 430
+    },
+    {
+      "epoch": 5.866666666666667,
+      "grad_norm": 53.5,
+      "kl": 0.0,
+      "learning_rate": 4.146666666666667e-07,
+      "logits/rejected": 1737012224.0,
+      "logps/rejected": -1625.72900390625,
+      "loss": 0.2277,
+      "rewards/rejected": -1.8366947174072266,
+      "step": 440
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 39.25,
+      "kl": 0.0,
+      "learning_rate": 4.0133333333333333e-07,
+      "logits/rejected": 1715832217.6,
+      "logps/rejected": -1501.8396484375,
+      "loss": 0.2283,
+      "rewards/rejected": -1.8582498550415039,
+      "step": 450
+    },
+    {
+      "epoch": 6.133333333333334,
+      "grad_norm": 55.25,
+      "kl": 47.387760162353516,
+      "learning_rate": 3.88e-07,
+      "logits/chosen": 1729806540.8,
+      "logps/chosen": -1536.3201171875,
+      "loss": 0.4921,
+      "rewards/chosen": 4.784424209594727,
+      "step": 460
+    },
+    {
+      "epoch": 6.266666666666667,
+      "grad_norm": 77.0,
+      "kl": 51.74030685424805,
+      "learning_rate": 3.7466666666666663e-07,
+      "logits/chosen": 1736568832.0,
+      "logps/chosen": -1627.24794921875,
+      "loss": 0.4934,
+      "rewards/chosen": 5.199858093261719,
+      "step": 470
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 61.75,
+      "kl": 53.5655517578125,
+      "learning_rate": 3.6133333333333334e-07,
+      "logits/chosen": 1746720563.2,
+      "logps/chosen": -1565.3529296875,
+      "loss": 0.4801,
+      "rewards/chosen": 5.444185256958008,
+      "step": 480
+    },
+    {
+      "epoch": 6.533333333333333,
+      "grad_norm": 40.75,
+      "kl": 47.25954055786133,
+      "learning_rate": 3.4799999999999994e-07,
+      "logits/chosen": 1744727741.8426967,
+      "logits/rejected": 1706023105.2075472,
+      "logps/chosen": -1587.4740168539327,
+      "logps/rejected": -1689.911704009434,
+      "loss": 0.4287,
+      "rewards/chosen": 5.714643957016619,
+      "rewards/margins": 7.034099805566516,
+      "rewards/rejected": -1.3194558485498968,
+      "step": 490
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 58.0,
+      "kl": 0.0,
+      "learning_rate": 3.3466666666666665e-07,
+      "logits/rejected": 1700372172.8,
+      "logps/rejected": -1541.06552734375,
+      "loss": 0.265,
+      "rewards/rejected": -1.5677401542663574,
+      "step": 500
     }
   ],
   "logging_steps": 10,