Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5f0f80818b900ea636e16b6d94c7e2467aea427218c5bfe12c8e544296a5be
+oid sha256:3938d37466941641e80467883ca7d7f0dc40a329ebb3457e573f37a8d193481c
 size 167832688

last-checkpoint/global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b5b3c77e3cc75122ce497af1ba7bb9dffe9c319715607fb79ccf63f8fcb97ee
+size 503344336

last-checkpoint/global_step100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5285b0c84a14ea96a7c1e52d0ab7b4a76bea5271f8a03c10407b5f936ad132fb
+size 503344464

last-checkpoint/global_step100/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00cffa2da684f6efaf23c43f7d0074caae4342a39aa24eb2c6a3ce0fa7f0555
+size 168117356

last-checkpoint/latest

@@ -1 +1 @@
-global_step90
+global_step100

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb97b24f34ff3e53eec5be9cf35c1a7161c58dbc2fed7dda160fb3eb64e5f353
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03283772689957128,
+  "epoch": 0.03648636322174587,
   "eval_steps": 500,
-  "global_step": 90,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1357,6 +1357,156 @@
       "rewards/margins": 15.75,
       "rewards/rejected": -14.375,
       "step": 90
+    },
+    {
+      "epoch": 0.03320259053178874,
+      "grad_norm": 2.3973431240165155e-08,
+      "learning_rate": 4.8943483704846475e-06,
+      "logits/chosen": -1.6171875,
+      "logits/rejected": -1.671875,
+      "logps/chosen": -148.0,
+      "logps/rejected": -392.0,
+      "loss": 0.0432,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.005859375,
+      "rewards/margins": 26.0,
+      "rewards/rejected": -26.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.0335674541640062,
+      "grad_norm": 6.508482933044434,
+      "learning_rate": 3.873830406168111e-06,
+      "logits/chosen": -1.5859375,
+      "logits/rejected": -1.5625,
+      "logps/chosen": -161.0,
+      "logps/rejected": -370.0,
+      "loss": 0.313,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.2734375,
+      "rewards/margins": 22.25,
+      "rewards/rejected": -21.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.03393231779622366,
+      "grad_norm": 0.001520270947366953,
+      "learning_rate": 2.970427372400353e-06,
+      "logits/chosen": -1.484375,
+      "logits/rejected": -1.546875,
+      "logps/chosen": -146.0,
+      "logps/rejected": -328.0,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.421875,
+      "rewards/margins": 20.0,
+      "rewards/rejected": -17.625,
+      "step": 93
+    },
+    {
+      "epoch": 0.03429718142844112,
+      "grad_norm": 0.0009259243379347026,
+      "learning_rate": 2.1852399266194314e-06,
+      "logits/chosen": -1.46875,
+      "logits/rejected": -1.4609375,
+      "logps/chosen": -184.0,
+      "logps/rejected": -316.0,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.169921875,
+      "rewards/margins": 18.75,
+      "rewards/rejected": -19.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.03466204506065858,
+      "grad_norm": 0.01026194542646408,
+      "learning_rate": 1.5192246987791981e-06,
+      "logits/chosen": -1.5078125,
+      "logits/rejected": -1.515625,
+      "logps/chosen": -202.0,
+      "logps/rejected": -462.0,
+      "loss": 0.0004,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -4.09375,
+      "rewards/margins": 24.25,
+      "rewards/rejected": -28.25,
+      "step": 95
+    },
+    {
+      "epoch": 0.03502690869287604,
+      "grad_norm": 1.1470707654953003,
+      "learning_rate": 9.731931258429638e-07,
+      "logits/chosen": -1.5625,
+      "logits/rejected": -1.6484375,
+      "logps/chosen": -198.0,
+      "logps/rejected": -364.0,
+      "loss": 0.0935,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -1.1328125,
+      "rewards/margins": 17.75,
+      "rewards/rejected": -18.75,
+      "step": 96
+    },
+    {
+      "epoch": 0.035391772325093496,
+      "grad_norm": 0.03475894406437874,
+      "learning_rate": 5.478104631726711e-07,
+      "logits/chosen": -1.5859375,
+      "logits/rejected": -1.640625,
+      "logps/chosen": -194.0,
+      "logps/rejected": -332.0,
+      "loss": 0.0871,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -4.71875,
+      "rewards/margins": 14.375,
+      "rewards/rejected": -19.125,
+      "step": 97
+    },
+    {
+      "epoch": 0.035756635957310955,
+      "grad_norm": 9.08543515834026e-05,
+      "learning_rate": 2.4359497401758024e-07,
+      "logits/chosen": -1.578125,
+      "logits/rejected": -1.546875,
+      "logps/chosen": -132.0,
+      "logps/rejected": -396.0,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 3.1875,
+      "rewards/margins": 26.5,
+      "rewards/rejected": -23.25,
+      "step": 98
+    },
+    {
+      "epoch": 0.036121499589528414,
+      "grad_norm": 0.3016016483306885,
+      "learning_rate": 6.09172980904238e-08,
+      "logits/chosen": -1.46875,
+      "logits/rejected": -1.390625,
+      "logps/chosen": -168.0,
+      "logps/rejected": -356.0,
+      "loss": 0.0063,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.4765625,
+      "rewards/margins": 20.5,
+      "rewards/rejected": -21.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.03648636322174587,
+      "grad_norm": 1.978473665076308e-05,
+      "learning_rate": 0.0,
+      "logits/chosen": -1.609375,
+      "logits/rejected": -1.5625,
+      "logps/chosen": -166.0,
+      "logps/rejected": -420.0,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.078125,
+      "rewards/margins": 27.5,
+      "rewards/rejected": -25.375,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -1371,7 +1521,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }