Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f96ce207444d7a10e17049c94dc5648bd8f200d8da34ca1d6852ec281d5c6819
+oid sha256:804a607f5bc7875b5255290292365e3c6ac847585ff434cabc2f3d5d24a00d2a
 size 18516456

last-checkpoint/global_step30/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05eb3a4f136a1958f3c5c416988ec786fd4c8d5d0643b737fc49f2dcf009470a
+size 13857360

last-checkpoint/global_step30/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ac6728dd0a4faffb6c1e6a3fdd75b56a85a6268fd94a7680afa248b3da8e75
+size 13856656

last-checkpoint/global_step30/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d52dd5892669f2296b0f1cd15f59f9b778781cd4d8fa46c605089268e3b4856
+size 13857360

last-checkpoint/global_step30/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73128a6936313c0b5c6441c7e184e66232d0f1e5d280a967a1f2869234377055
+size 13856656

last-checkpoint/global_step30/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d068e0becce39bb30539549ecb05d3b848255e1180e7e11dd1532e210ded51de
+size 13857424

last-checkpoint/global_step30/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8bf5e83c4a91c075d1a231f4d410dd31390a15ee5ade745981888f1b0ccfa59
+size 13856656

last-checkpoint/global_step30/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d528ba595355b52cd6de62323f9d86bbebd02f2ccaa1e00133bd6e6d0053de16
+size 13857424

last-checkpoint/global_step30/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82543bbd7216ed705c94af8b6cfce2860bafd6d698a86c7293702a9ad967ff86
+size 13856656

last-checkpoint/global_step30/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8414e911efad872d067efb4e057790ccd411733f208e2dfd83b1bcf8dfe342a
+size 485512632

last-checkpoint/latest

@@ -1 +1 @@
-global_step24
+global_step30

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9527d2431b9400e39f4784d5d63151434952de4dfec19feb2ab624b5f1922cb0
+oid sha256:e61694caed75a4de60717c7522cd2bcddf9803313b4abf292318bb17a445487e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08613728129205922,
+  "epoch": 0.10767160161507403,
   "eval_steps": 500,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -368,6 +368,96 @@
       "rewards/margins": 0.2939453125,
       "rewards/rejected": 0.05828094482421875,
       "step": 24
+    },
+    {
+      "epoch": 0.08972633467922836,
+      "grad_norm": 0.5010308027267456,
+      "learning_rate": 4.06547058867883e-06,
+      "logits/chosen": -0.87158203125,
+      "logits/rejected": -1.21484375,
+      "logps/chosen": -532.75,
+      "logps/rejected": -346.25,
+      "loss": 0.5499,
+      "rewards/accuracies": 0.765625,
+      "rewards/chosen": 0.373779296875,
+      "rewards/margins": 0.337646484375,
+      "rewards/rejected": 0.03619384765625,
+      "step": 25
+    },
+    {
+      "epoch": 0.09331538806639748,
+      "grad_norm": 0.5847342014312744,
+      "learning_rate": 2.86474508437579e-06,
+      "logits/chosen": -0.861328125,
+      "logits/rejected": -1.162109375,
+      "logps/chosen": -524.25,
+      "logps/rejected": -364.0,
+      "loss": 0.5534,
+      "rewards/accuracies": 0.8046875,
+      "rewards/chosen": 0.3896484375,
+      "rewards/margins": 0.3223876953125,
+      "rewards/rejected": 0.0676116943359375,
+      "step": 26
+    },
+    {
+      "epoch": 0.09690444145356662,
+      "grad_norm": 0.5329582095146179,
+      "learning_rate": 1.8553997993420495e-06,
+      "logits/chosen": -0.9013671875,
+      "logits/rejected": -1.12451171875,
+      "logps/chosen": -544.25,
+      "logps/rejected": -378.75,
+      "loss": 0.583,
+      "rewards/accuracies": 0.7109375,
+      "rewards/chosen": 0.317138671875,
+      "rewards/margins": 0.24462890625,
+      "rewards/rejected": 0.07248687744140625,
+      "step": 27
+    },
+    {
+      "epoch": 0.10049349484073576,
+      "grad_norm": 0.5788964629173279,
+      "learning_rate": 1.0533527116762298e-06,
+      "logits/chosen": -0.830078125,
+      "logits/rejected": -1.13916015625,
+      "logps/chosen": -501.25,
+      "logps/rejected": -367.75,
+      "loss": 0.5667,
+      "rewards/accuracies": 0.8359375,
+      "rewards/chosen": 0.368896484375,
+      "rewards/margins": 0.321533203125,
+      "rewards/rejected": 0.047332763671875,
+      "step": 28
+    },
+    {
+      "epoch": 0.10408254822790489,
+      "grad_norm": 0.5081790685653687,
+      "learning_rate": 4.7125258307053385e-07,
+      "logits/chosen": -0.89208984375,
+      "logits/rejected": -1.15283203125,
+      "logps/chosen": -516.0,
+      "logps/rejected": -350.75,
+      "loss": 0.5557,
+      "rewards/accuracies": 0.8046875,
+      "rewards/chosen": 0.3759765625,
+      "rewards/margins": 0.31689453125,
+      "rewards/rejected": 0.059051513671875,
+      "step": 29
+    },
+    {
+      "epoch": 0.10767160161507403,
+      "grad_norm": 0.6344053745269775,
+      "learning_rate": 1.1827948028283353e-07,
+      "logits/chosen": -0.79736328125,
+      "logits/rejected": -1.0771484375,
+      "logps/chosen": -549.75,
+      "logps/rejected": -358.0,
+      "loss": 0.5547,
+      "rewards/accuracies": 0.8203125,
+      "rewards/chosen": 0.364013671875,
+      "rewards/margins": 0.3228759765625,
+      "rewards/rejected": 0.0411224365234375,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -382,7 +472,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }