Training in progress, step 750, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fa05163bed9a1cd36363dd4ff80562137d5f68770c186539473124d4551083
+oid sha256:a4557fcf116808896585a0b9fba254579763e6927b7ad0e5de2ed4ff34077d20
 size 4962001760

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da931ba763893ccb98dc512107b6b5c263eca97cd13e5b05ac86947b959fc7da
+oid sha256:9891b26db54b0fe9429d1eaae88b62639a1a39212715f41b52512ae92fa70832
 size 4915916160

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52dcde588022fc935bedd4afcd81e6f4e1b41f079db26834e38267f75b98e817
+oid sha256:138e574470736c7298b3c5a8a8b3b18aefe390eaac6f2f638335790ebc1cb485
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1642b4a6158c2fd2540216fefd044c2d03795ab85a18a37a96ff8990efe21e7a
+oid sha256:e6041069b5d927dee319955f65316f6e8fdb6f91cb75c2ce021a6fda24bfc8e7
 size 1623221024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb389ace5a850a48e09909591bc0839eabefd253110f1ce6ef4f82c311105c39
+oid sha256:dae74fef979973d18fe3467c0e7c2f65c81fbe34c1496da6ee9e440f4ed289ce
 size 13053963

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0da242ef698d1e1ed5421e6b23d1b44f93a6a55dcb1a127cd8931c14bd84e798
+oid sha256:47aaa76b87f4c23b4d68cb4239507aa4eae30749e5f68da918a711350817ab21
 size 16389

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c84fd50bb0fe9f0aa26725966ffc16f69210c4dc450904bc61526922ca0cae8b
+oid sha256:b1bc421bbf7cb973e5a2ee6575b3d963663503f32fac096384d80658aa160982
 size 16389

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d28d7579b85bd847de486eff8a19da23bfa22d830f81a69f170a6ac10defb69
+oid sha256:e2c6958cc066428807adb00f4692d3c352b3308f598be90eebe8e0669807f9ab
 size 16389

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5d0fa36258fc125bd8dc7fbf20d2fa389251a7d5e275c5c7a393818ce55fa5
+oid sha256:60fd83ff2a53a6695bc067ad08f0a8eba7e528c1e79e11672a503c27108310a2
 size 16389

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:726101b9f924215ed50f082b1e89969dff616b826c0c2b64bd1221baa108c357
+oid sha256:cb0f3bfe3c5520a616527742a7e4aa9e3609c6434bc9e0a1ce9481706223bf33
 size 16389

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c55b96aa4759bfcbcc6b0d85681eebff0595b41c99b9a11340f9a8e78bff69
+oid sha256:485aa82032edff97f9113166b023e2a53f833c71ba864fa3342d7671bea4fef4
 size 16389

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2fbc025fa229f4a96f9a30abe9f81e3829db7eae80a3909a4d421e8abeee73
+oid sha256:1713e23bed215f279ff7d13156cf1fcb32a197abfcc8243ab01a3f13f7a8e4fb
 size 16389

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab5ad9877076fc54a96b83cdb0188bb8bad71aa0e4038145c7fc0725631af546
+oid sha256:6b9d696391ce1a68adcb25acaf87c9c5f9d4a3c8c012dc0ada9067d146c6688a
 size 16389

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537e8778e25faae48041764f389414d8ae2bc54743a220f0eba2e87e988c3690
+oid sha256:9b8700635e39226de388de06c31a4d44ee2eac31b86ae5fe6d282b60ff442a2a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.333333333333334,
+  "epoch": 10.0,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -845,6 +845,65 @@
       "loss": 0.4805,
       "rewards/chosen": 5.435222625732422,
       "step": 700
+    },
+    {
+      "epoch": 9.466666666666667,
+      "grad_norm": 46.75,
+      "kl": 56.87353515625,
+      "learning_rate": 5.4666666666666666e-08,
+      "logits/chosen": 1751316684.8,
+      "logps/chosen": -1617.39033203125,
+      "loss": 0.4885,
+      "rewards/chosen": 5.705249786376953,
+      "step": 710
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 38.25,
+      "kl": 17.8724308013916,
+      "learning_rate": 4.133333333333333e-08,
+      "logits/chosen": 1729312212.9345794,
+      "logits/rejected": 1699881844.5821595,
+      "logps/chosen": -1447.3971962616822,
+      "logps/rejected": -1524.6291079812206,
+      "loss": 0.2937,
+      "rewards/chosen": 5.578735921984521,
+      "rewards/margins": 7.396489386947476,
+      "rewards/rejected": -1.8177534649629548,
+      "step": 720
+    },
+    {
+      "epoch": 9.733333333333333,
+      "grad_norm": 30.375,
+      "kl": 0.0,
+      "learning_rate": 2.8e-08,
+      "logits/rejected": 1695596134.4,
+      "logps/rejected": -1616.91201171875,
+      "loss": 0.2028,
+      "rewards/rejected": -2.142536735534668,
+      "step": 730
+    },
+    {
+      "epoch": 9.866666666666667,
+      "grad_norm": 42.5,
+      "kl": 0.0,
+      "learning_rate": 1.4666666666666666e-08,
+      "logits/rejected": 1732339097.6,
+      "logps/rejected": -1627.45458984375,
+      "loss": 0.211,
+      "rewards/rejected": -2.0092498779296877,
+      "step": 740
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 42.0,
+      "kl": 0.0,
+      "learning_rate": 1.3333333333333333e-09,
+      "logits/rejected": 1714343731.2,
+      "logps/rejected": -1500.21591796875,
+      "loss": 0.2487,
+      "rewards/rejected": -1.6958515167236328,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -859,7 +918,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }