Training in progress, step 160, checkpoint

last-checkpoint/global_step160/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13262f4ec724ad31a8660a1affd3ddf32bfa3192263e5c9df5d86786049bb12d
+size 24090817920

last-checkpoint/global_step160/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:fc1d0cc1014465fad2660b31f94c00c1d7b7cae326307a746c351cfc8b9ecd79
+size 24090819136

last-checkpoint/global_step160/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aab651026705422b2c7ac31cae73a69fcce0360065b1c10e844bc031761b6a5
+size 24090819456

last-checkpoint/global_step160/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e581d8fbbf9e77fef0ef336273efc0ca1a392c412b83ecb1365583dde0c5dca
+size 24090817664

last-checkpoint/global_step160/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6de4fbfef4d4c0a535b5645e9f131adf64ac92db47527c329ea6211139b89dd
+size 16060626872

last-checkpoint/latest

@@ -1 +1 @@
-global_step150
+global_step160

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba7ee1b217c55d2fa7f85d15da85832a49af019e79b9dcb41041b39ef6b568ab
+oid sha256:c85b9f7e814564e45e820e103071afb8b9f543d0738f4867b54c4b7022de1f84
 size 4976706864

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d67d3599c884ec95539551820c688c492d51fa280e6cf51b335f387ddb472a
+oid sha256:0aebfaf502da60362798931274abfb647ce50a482f753af9f5ffe6b0594526f9
 size 4999802720

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6585d5b078cc01846c9949de2af57cf41e74686c7a08bc6790f29c6d37f7338
+oid sha256:637b2731b51a4b1a71bc5bd303e5d86541bd80b2a3d6f8db7dfa716fdbecaa58
 size 4915916176

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:089c8be291e057156ab12f6b26d28522b290ebca0159792fac09016abf7d018d
+oid sha256:492467668fa975321168a84f2ea5d71e1d164dbcaba6caf6df3e90462b5283be
 size 1168147000

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629e864ced66f39ea03a72fd6cab50c6ad98690ab269bdfb2d15f1f0cb819494
+oid sha256:f049945e61eb1d7f93c376fde3da0c282d1e7e64029bf29674b773c6cf38f57a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8739020105406987,
+  "epoch": 1.998828811243412,
   "eval_steps": 75,
-  "global_step": 150,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1164,6 +1164,81 @@
       "eval_samples_per_second": 3.395,
       "eval_steps_per_second": 0.849,
       "step": 150
+    },
+    {
+      "epoch": 1.8988873706812415,
+      "grad_norm": 8.195993031555705,
+      "learning_rate": 8.645454235739902e-09,
+      "logits/chosen": -0.676539957523346,
+      "logits/rejected": -0.7394694685935974,
+      "logps/chosen": -181.1811065673828,
+      "logps/rejected": -207.39080810546875,
+      "loss": 0.2738,
+      "rewards/accuracies": 0.921875,
+      "rewards/chosen": -1.422343373298645,
+      "rewards/margins": 1.9836503267288208,
+      "rewards/rejected": -3.405993700027466,
+      "step": 152
+    },
+    {
+      "epoch": 1.9238727308217842,
+      "grad_norm": 7.242463445087286,
+      "learning_rate": 4.8943483704846465e-09,
+      "logits/chosen": -0.656994104385376,
+      "logits/rejected": -0.7103748321533203,
+      "logps/chosen": -183.3748321533203,
+      "logps/rejected": -188.81219482421875,
+      "loss": 0.2718,
+      "rewards/accuracies": 0.89453125,
+      "rewards/chosen": -1.4463797807693481,
+      "rewards/margins": 1.880941390991211,
+      "rewards/rejected": -3.3273210525512695,
+      "step": 154
+    },
+    {
+      "epoch": 1.9488580909623268,
+      "grad_norm": 6.9367447852277575,
+      "learning_rate": 2.1852399266194312e-09,
+      "logits/chosen": -0.6909129619598389,
+      "logits/rejected": -0.7760818004608154,
+      "logps/chosen": -177.80374145507812,
+      "logps/rejected": -266.32806396484375,
+      "loss": 0.2686,
+      "rewards/accuracies": 0.92578125,
+      "rewards/chosen": -1.4405275583267212,
+      "rewards/margins": 2.0439579486846924,
+      "rewards/rejected": -3.484485626220703,
+      "step": 156
+    },
+    {
+      "epoch": 1.9738434511028693,
+      "grad_norm": 7.621192478848495,
+      "learning_rate": 5.47810463172671e-10,
+      "logits/chosen": -0.6629250049591064,
+      "logits/rejected": -0.7373142242431641,
+      "logps/chosen": -183.51670837402344,
+      "logps/rejected": -190.675537109375,
+      "loss": 0.2845,
+      "rewards/accuracies": 0.921875,
+      "rewards/chosen": -1.451604962348938,
+      "rewards/margins": 2.0776655673980713,
+      "rewards/rejected": -3.5292704105377197,
+      "step": 158
+    },
+    {
+      "epoch": 1.998828811243412,
+      "grad_norm": 7.292176844709846,
+      "learning_rate": 0.0,
+      "logits/chosen": -0.745610773563385,
+      "logits/rejected": -0.8196827173233032,
+      "logps/chosen": -172.93553161621094,
+      "logps/rejected": -271.3219299316406,
+      "loss": 0.264,
+      "rewards/accuracies": 0.9140625,
+      "rewards/chosen": -1.2879290580749512,
+      "rewards/margins": 2.1956043243408203,
+      "rewards/rejected": -3.4835333824157715,
+      "step": 160
     }
   ],
   "logging_steps": 2,
@@ -1178,7 +1253,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }