Training in progress, step 200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81403bfcf9f6f68cd9fc54e0cb2ffa9abcc83dc33a871641f3c002bf62557a48
+oid sha256:d6d7bb49a546070d0f06db42d905c28e11210d2dd3a84556f9776bbdb1c72515
 size 4962001760

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b4fd8fa570356e5c7c5daddd5572ac53e4be6f526f326399b38011e2987819
+oid sha256:e7cf2d25394898ae6c044195e091f0137da5d97c36fdcf256310291b6c788153
 size 4915916160

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98165cfaa1490aeda4b0c8ed8de75acd74b56b8b69c49e61b1b33f56ec8a257b
+oid sha256:e7b626ddfa7b2b2f6c99cb6edd374324fe1cc409795921848907a0fe580e3ae5
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73155fb39dceb7f3b6f085b8a907d5140cfa9594ac6cc2a704156f7c478b0de5
+oid sha256:9155e26da421bd5d4381861155dc2bb5b7da6d04160fa66c7db3e3f4bc84ac41
 size 1623221024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06bf1b973b2401107f15e6e3ca2c3e3fb22511443d8be1b341ff178e3b2f2c3a
+oid sha256:d331ef78c125b3b95b357c580a6966cc0242f5c30f3e85c0ea4b7924ca469750
 size 13053643

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:679f35580a12e62422982f35c3522578e56c008471254f1009231e45c61c4825
+oid sha256:575512e9c00b18ee70c366f67b2b0f002290285083714312b8bf78b36aeea0c5
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe3018d6e741416daf665d124dbfd121403ad18a5a16910eef763332b877bbe
+oid sha256:870871eb5e1c3f4436d61b35649980a174de89fb8ad9788f2d73e82294209354
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae1a9995ee6abb57005fc577beb0223dc9ec16db52d502be5e87d82ccd3d8e40
+oid sha256:94ff12f33aef0e4cfef98b601f4c6d3d0beb4abced43c5f557c11bc4ce3ddf53
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd9384e3fc2397abee093eb4c04a97a73faa72ae89bb6f004af32bc617b16e5
+oid sha256:7fbf244dea2f57f580c016311c28847fdf6a8d0d8af08ed4d78d75d102da168c
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786bb3e4420df6a45ec309f3d32816d8539d3c453e04d4a62d575988cbcfc0d8
+oid sha256:99908a68d404fdefbbfa797eb2f5eb9f75a3a37d1b8fdab17f87efbde6f4ce4f
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace6e4353e86c18ad4b80aff4ec738a6bcebbc84b3f80f96efad05f476972479
+oid sha256:52f189356a4e5d077c8438dd9c08ba1a692ac0e78f07054f726870cec5093c7e
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87ea1f71558dbc045993b91541af3e5fb5552ad051c7ea55c1b4d451d59017eb
+oid sha256:211015dbfc9200331d3401fde9ae901b6bd709c00b3c545bad1187ac833c5739
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65150b1b20a1ac491a43c273478d76a002a4600d12c8ce10ae5b140d903a965f
+oid sha256:730c163411d01a0423c98cd2284d621aa5f8be1b009f2a5fcf413bdbd89e32c4
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10006678a6909b7aa12a426cd3bdd4f98bbdc35e348b7d8c18e2dc94db15e30d
+oid sha256:87ebe31a6312a81e5b51b292be97bf6be0c0e133978c540813601a19980f8814
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3333333333333333,
+  "epoch": 2.6666666666666665,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -137,6 +137,124 @@
       "loss": 0.4936,
       "rewards/chosen": 3.1399845123291015,
       "step": 100
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 47.75,
+      "kl": 42.36182403564453,
+      "learning_rate": 8.546666666666666e-07,
+      "logits/chosen": 1819451801.6,
+      "logps/chosen": -1631.21865234375,
+      "loss": 0.4832,
+      "rewards/chosen": 4.322412109375,
+      "step": 110
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 65.0,
+      "kl": 29.110525131225586,
+      "learning_rate": 8.413333333333333e-07,
+      "logits/chosen": 1786882220.2616823,
+      "logits/rejected": 1767476998.0093896,
+      "logps/chosen": -1454.260660046729,
+      "logps/rejected": -1486.950850938967,
+      "loss": 0.4809,
+      "rewards/chosen": 4.8924052871276285,
+      "rewards/margins": 2.9423321882151434,
+      "rewards/rejected": 1.9500730989124853,
+      "step": 120
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 68.0,
+      "kl": 10.5321044921875,
+      "learning_rate": 8.28e-07,
+      "logits/rejected": 1757802086.4,
+      "logps/rejected": -1584.4416015625,
+      "loss": 0.4952,
+      "rewards/rejected": 1.1045079231262207,
+      "step": 130
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 74.5,
+      "kl": 2.656236171722412,
+      "learning_rate": 8.146666666666666e-07,
+      "logits/rejected": 1784456601.6,
+      "logps/rejected": -1606.92255859375,
+      "loss": 0.4411,
+      "rewards/rejected": 0.04395853877067566,
+      "step": 140
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 47.25,
+      "kl": 0.02235652133822441,
+      "learning_rate": 8.013333333333333e-07,
+      "logits/rejected": 1755790950.4,
+      "logps/rejected": -1492.91025390625,
+      "loss": 0.3227,
+      "rewards/rejected": -0.965308952331543,
+      "step": 150
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 74.5,
+      "kl": 22.667367935180664,
+      "learning_rate": 7.88e-07,
+      "logits/chosen": 1760644710.4,
+      "logps/chosen": -1561.63623046875,
+      "loss": 0.5121,
+      "rewards/chosen": 2.2527976989746095,
+      "step": 160
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 75.5,
+      "kl": 35.21966552734375,
+      "learning_rate": 7.746666666666666e-07,
+      "logits/chosen": 1774286233.6,
+      "logps/chosen": -1643.762109375,
+      "loss": 0.4987,
+      "rewards/chosen": 3.5484432220458983,
+      "step": 170
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 52.25,
+      "kl": 43.11100387573242,
+      "learning_rate": 7.613333333333333e-07,
+      "logits/chosen": 1786122035.2,
+      "logps/chosen": -1576.08076171875,
+      "loss": 0.4918,
+      "rewards/chosen": 4.371388244628906,
+      "step": 180
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 49.75,
+      "kl": 43.39256286621094,
+      "learning_rate": 7.48e-07,
+      "logits/chosen": 1780707128.5692885,
+      "logits/rejected": 1751267212.0754716,
+      "logps/chosen": -1593.653675093633,
+      "logps/rejected": -1665.3343160377358,
+      "loss": 0.481,
+      "rewards/chosen": 5.09666597173455,
+      "rewards/margins": 3.9583941361195003,
+      "rewards/rejected": 1.13827183561505,
+      "step": 190
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 63.5,
+      "kl": 5.4629011154174805,
+      "learning_rate": 7.346666666666666e-07,
+      "logits/rejected": 1737874841.6,
+      "logps/rejected": -1520.10458984375,
+      "loss": 0.4785,
+      "rewards/rejected": 0.5283474445343017,
+      "step": 200
     }
   ],
   "logging_steps": 10,