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 sha256:6f6e3c73c4b677a372e53835ce1c465beff91e2ebf0237e5d37bdef4929629ac
+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:edddca56a562ac53e9c263e80e5245c04c6daa626580914cd90017b21e598396
+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 sha256:7ab7bde144afc4d467647ea4c3fe33799cd1362c50d5fd214fddaa61f009acab
+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 sha256:02906abf359d7dfd745838e4f1c5cbd96ea61510faa06dc6464837764da4b0d2
+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 sha256:1deede2bf2e2780f10cec981f4d7461d6657b9ad68d19b91647bd7c9f7a45814
+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 sha256:603c3ce2340cdb4543967cf9966accc234ae0ad952e44808b33ad7aa8a05ca2c
+oid sha256:53aa1c5aa28498eb2c975eddd342eab2b54372f83dcfcfa429d8092b78560640
 size 4976706864

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf3c4f3f7ccc3ebbe228696c78a9200be54d3ddc124b8d965d9598a3c213fbc
+oid sha256:4ea6dc47ccd7b80d3a4a2a760e76386722ea412c422816d6d1361854a0d78dac
 size 4999802720

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303561de756b286a1459f34c3bacf31c5949e7cc2c7042fe1b03700f35cab4f6
+oid sha256:f6910a92d4b64ed6bf457bf455f1c1d80a7b141d7be13ae3f2ccfb74d9be9688
 size 4915916176

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f52d45d1ed117f8493019fc364eb54838fc2e6ea652681a8882bdb1550bdfb5
+oid sha256:8342e315531b084879f0a23af6be6194a657993bfaf872a104e7dcfe535b3f12
 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": 3.261,
       "eval_steps_per_second": 0.815,
       "step": 150
+    },
+    {
+      "epoch": 1.8988873706812415,
+      "grad_norm": 8.503745608023737,
+      "learning_rate": 8.645454235739902e-09,
+      "logits/chosen": -0.7426515817642212,
+      "logits/rejected": -0.8051266670227051,
+      "logps/chosen": -195.47421264648438,
+      "logps/rejected": -199.013916015625,
+      "loss": 0.2643,
+      "rewards/accuracies": 0.9140625,
+      "rewards/chosen": 0.39815255999565125,
+      "rewards/margins": 2.137446403503418,
+      "rewards/rejected": -1.7392936944961548,
+      "step": 152
+    },
+    {
+      "epoch": 1.9238727308217842,
+      "grad_norm": 8.367825814127663,
+      "learning_rate": 4.8943483704846465e-09,
+      "logits/chosen": -0.7322957515716553,
+      "logits/rejected": -0.7974464893341064,
+      "logps/chosen": -193.97613525390625,
+      "logps/rejected": -191.2456817626953,
+      "loss": 0.2622,
+      "rewards/accuracies": 0.921875,
+      "rewards/chosen": 0.45596182346343994,
+      "rewards/margins": 2.185451030731201,
+      "rewards/rejected": -1.7294889688491821,
+      "step": 154
+    },
+    {
+      "epoch": 1.9488580909623268,
+      "grad_norm": 7.920183430972945,
+      "learning_rate": 2.1852399266194312e-09,
+      "logits/chosen": -0.7559969425201416,
+      "logits/rejected": -0.8131712079048157,
+      "logps/chosen": -203.8223876953125,
+      "logps/rejected": -202.947509765625,
+      "loss": 0.2773,
+      "rewards/accuracies": 0.91015625,
+      "rewards/chosen": 0.32228347659111023,
+      "rewards/margins": 2.08817458152771,
+      "rewards/rejected": -1.7658910751342773,
+      "step": 156
+    },
+    {
+      "epoch": 1.9738434511028693,
+      "grad_norm": 8.06856390519066,
+      "learning_rate": 5.47810463172671e-10,
+      "logits/chosen": -0.7470804452896118,
+      "logits/rejected": -0.8129448294639587,
+      "logps/chosen": -210.6734619140625,
+      "logps/rejected": -196.4785919189453,
+      "loss": 0.2755,
+      "rewards/accuracies": 0.890625,
+      "rewards/chosen": 0.42607438564300537,
+      "rewards/margins": 2.0202014446258545,
+      "rewards/rejected": -1.5941270589828491,
+      "step": 158
+    },
+    {
+      "epoch": 1.998828811243412,
+      "grad_norm": 9.773194489937959,
+      "learning_rate": 0.0,
+      "logits/chosen": -0.80845707654953,
+      "logits/rejected": -0.8671077489852905,
+      "logps/chosen": -203.4849853515625,
+      "logps/rejected": -204.71002197265625,
+      "loss": 0.2941,
+      "rewards/accuracies": 0.91796875,
+      "rewards/chosen": 0.35994353890419006,
+      "rewards/margins": 2.0885844230651855,
+      "rewards/rejected": -1.7286407947540283,
+      "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": {}
     }