Training in progress, step 700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c243598c92aa172639ff6e40dd1b983ce2b906a69338a7f68bb077d0b49af2
+oid sha256:e5fa05163bed9a1cd36363dd4ff80562137d5f68770c186539473124d4551083
 size 4962001760

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97de6841f7a06df63f15116413b63a6d8f0ed1481c73daec4d308907b9ef7477
+oid sha256:da931ba763893ccb98dc512107b6b5c263eca97cd13e5b05ac86947b959fc7da
 size 4915916160

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df52273384350aee9baa269ceb1e9e573aeaf2a7566f394660f38eefd4989e8
+oid sha256:52dcde588022fc935bedd4afcd81e6f4e1b41f079db26834e38267f75b98e817
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff86115c9ca1a90bf6873583c738e398f9f9947c13c68352f73a518f1bd9b44
+oid sha256:1642b4a6158c2fd2540216fefd044c2d03795ab85a18a37a96ff8990efe21e7a
 size 1623221024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554d638b6db84406c05520b337e63b464c5dd4ca01d9e36368adbd26b62126ee
+oid sha256:fb389ace5a850a48e09909591bc0839eabefd253110f1ce6ef4f82c311105c39
 size 13053963

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6954e89c1960fa7ad6ea4d0b8bbf7ab04896fa485702dacc91479549c4c5f5bd
+oid sha256:0da242ef698d1e1ed5421e6b23d1b44f93a6a55dcb1a127cd8931c14bd84e798
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39430be47ab0759ba4c6b2029bf2ac1430c442bd0153447dadb3e88ceeace01f
+oid sha256:c84fd50bb0fe9f0aa26725966ffc16f69210c4dc450904bc61526922ca0cae8b
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e70cc76576adfb81afd443354dc1068743c58308fe7d889099fbeedaa0a7788
+oid sha256:8d28d7579b85bd847de486eff8a19da23bfa22d830f81a69f170a6ac10defb69
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a75d5f02ca237d8ef45529e298315fb70e4bd993cf96fd04ae998cf9895b3c4
+oid sha256:ed5d0fa36258fc125bd8dc7fbf20d2fa389251a7d5e275c5c7a393818ce55fa5
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6680063dc12b212232a97593d0ad4ca30bf709a7f3fc4f37444f622689ee4b
+oid sha256:726101b9f924215ed50f082b1e89969dff616b826c0c2b64bd1221baa108c357
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d575736283b8fd594e1e1fc04ebb33a9123b2d46d9a7f2b36ee599ae2efdf4fa
+oid sha256:94c55b96aa4759bfcbcc6b0d85681eebff0595b41c99b9a11340f9a8e78bff69
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6501ba3ee593e553d24857a1d06a2ae89d416a291843a7f705be771a8677fb
+oid sha256:3f2fbc025fa229f4a96f9a30abe9f81e3829db7eae80a3909a4d421e8abeee73
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee4b071aa28acd8e61610943b47f7a78b87ce3fa1a3a7004c67f45adf039ffbe
+oid sha256:ab5ad9877076fc54a96b83cdb0188bb8bad71aa0e4038145c7fc0725631af546
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09ab206d51e08db07522003a69609e8e727f47b95ea47e6b2b8aa03687721b3
+oid sha256:537e8778e25faae48041764f389414d8ae2bc54743a220f0eba2e87e988c3690
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
+  "epoch": 9.333333333333334,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -727,6 +727,124 @@
       "loss": 0.241,
       "rewards/rejected": -1.795237922668457,
       "step": 600
+    },
+    {
+      "epoch": 8.133333333333333,
+      "grad_norm": 55.0,
+      "kl": 51.67559051513672,
+      "learning_rate": 1.88e-07,
+      "logits/chosen": 1727099904.0,
+      "logps/chosen": -1532.07939453125,
+      "loss": 0.4961,
+      "rewards/chosen": 5.208480453491211,
+      "step": 610
+    },
+    {
+      "epoch": 8.266666666666667,
+      "grad_norm": 64.5,
+      "kl": 54.74528884887695,
+      "learning_rate": 1.7466666666666667e-07,
+      "logits/chosen": 1733115904.0,
+      "logps/chosen": -1624.519921875,
+      "loss": 0.5013,
+      "rewards/chosen": 5.472665786743164,
+      "step": 620
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 54.75,
+      "kl": 54.551849365234375,
+      "learning_rate": 1.6133333333333332e-07,
+      "logits/chosen": 1742884659.2,
+      "logps/chosen": -1564.97412109375,
+      "loss": 0.4915,
+      "rewards/chosen": 5.482054138183594,
+      "step": 630
+    },
+    {
+      "epoch": 8.533333333333333,
+      "grad_norm": 30.625,
+      "kl": 46.306522369384766,
+      "learning_rate": 1.4799999999999998e-07,
+      "logits/chosen": 1739496766.3220973,
+      "logits/rejected": 1702134687.3962264,
+      "logps/chosen": -1588.0999531835207,
+      "logps/rejected": -1696.4740566037735,
+      "loss": 0.4184,
+      "rewards/chosen": 5.652020515127575,
+      "rewards/margins": 7.627730826153518,
+      "rewards/rejected": -1.9757103110259433,
+      "step": 640
+    },
+    {
+      "epoch": 8.666666666666666,
+      "grad_norm": 56.5,
+      "kl": 0.0,
+      "learning_rate": 1.3466666666666665e-07,
+      "logits/rejected": 1696173260.8,
+      "logps/rejected": -1544.7572265625,
+      "loss": 0.2282,
+      "rewards/rejected": -1.9369186401367187,
+      "step": 650
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 36.75,
+      "kl": 0.0,
+      "learning_rate": 1.2133333333333333e-07,
+      "logits/rejected": 1725317120.0,
+      "logps/rejected": -1612.53291015625,
+      "loss": 0.2132,
+      "rewards/rejected": -1.9934148788452148,
+      "step": 660
+    },
+    {
+      "epoch": 8.933333333333334,
+      "grad_norm": 43.25,
+      "kl": 0.0,
+      "learning_rate": 1.0799999999999999e-07,
+      "logits/rejected": 1711136563.2,
+      "logps/rejected": -1633.72958984375,
+      "loss": 0.2084,
+      "rewards/rejected": -2.079827880859375,
+      "step": 670
+    },
+    {
+      "epoch": 9.066666666666666,
+      "grad_norm": 74.5,
+      "kl": 26.150564193725586,
+      "learning_rate": 9.466666666666665e-08,
+      "logits/chosen": 1734777036.8,
+      "logits/rejected": 1720304844.8,
+      "logps/chosen": -1634.3982421875,
+      "logps/rejected": -1376.32314453125,
+      "loss": 0.3847,
+      "rewards/chosen": 5.2918556213378904,
+      "rewards/margins": 6.881484413146973,
+      "rewards/rejected": -1.5896287918090821,
+      "step": 680
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 45.0,
+      "kl": 54.32807540893555,
+      "learning_rate": 8.133333333333332e-08,
+      "logits/chosen": 1726023270.4,
+      "logps/chosen": -1519.271875,
+      "loss": 0.4882,
+      "rewards/chosen": 5.484774017333985,
+      "step": 690
+    },
+    {
+      "epoch": 9.333333333333334,
+      "grad_norm": 51.75,
+      "kl": 53.640716552734375,
+      "learning_rate": 6.8e-08,
+      "logits/chosen": 1733355929.6,
+      "logps/chosen": -1606.2349609375,
+      "loss": 0.4805,
+      "rewards/chosen": 5.435222625732422,
+      "step": 700
     }
   ],
   "logging_steps": 10,