Training in progress, step 186, checkpoint

last-checkpoint/global_step186/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096a578f428564b6129677fdf61da4d13b03e34d2108e66b580f0ac656a3f2f1
+size 14483467880

last-checkpoint/global_step186/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:cbc6a8c73419a47d2b475ee7749efbac0d5a43efe114a200c77985117141a6b9
+size 14483467880

last-checkpoint/global_step186/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d38166cf6f770126e20d77e8fde18633aaec70af875bd036a5b14ebe1aca751
+size 14483467880

last-checkpoint/global_step186/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:b19556227a45da1efefdd4ec6f1fc2ca21a862fa4797f32848c5122c1730447b
+size 14483467880

last-checkpoint/global_step186/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d46eadc8dd091805d3fa5518794219ead4f81092e939ec700eac380d199bb32
+size 150629

last-checkpoint/global_step186/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b1a3ae4b2dd3e4e3a1d3a9656982e2db29f94d41b025e84b90ff2d8e24ab24
+size 150629

last-checkpoint/global_step186/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ba54113b1de5eb6d92ee4cf1e2bf043ba1d0130c9c18a44b7b66dacb31a676
+size 150629

last-checkpoint/global_step186/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c265844cae92269763f88a8c218c1b2e74fb33791139bc5d8b6e880c8b2a5f
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step124
+global_step186

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5ef837fbded3b18cd0a4c60904eea5a7736290649d3272b2d4d747062f78dca
+oid sha256:a86ddf4ca1c25503e71e7f08d6596d0773148bd1af28bc8f2c1a7165ea636a1d
 size 4943162336

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94825f39a3c46a97f26e600562154fe1141d122c3aed77b1c8207909e2d39dd3
+oid sha256:94333f558ff69c31fb1fb843a840e7ebfda4e3534d6404c0dfb993ceaede38e8
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc54b0a6d0a78d822a62f65c8269ae1cd3e47b5d8ee2bbc91a50cad768ab180
+oid sha256:fdc022c32b0063f7be7c5541e0cb999e9e9d168f2aa00002bed63bd368a24152
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82e580e4e92d21ee2fca0348b8c83585fc265a3bdec704f0dbfaf6f2f800587
+oid sha256:50ca27603f7c4a4d9a980223e1a102922ac31561acfa7da4f28042e4e8b3528b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f5b0e26d51388f8180f8023bedbf0f066c7e40bd40eba6f2df3d9d9be582f4
+oid sha256:c57f658c3d9b6de611da50021823095fc4067036fb9a4b34655cc2e34fbf5c2b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c4a2665fddc1defbf2e5e1c0f3875ebfe701d33e843d7bd93ecde03037e001
+oid sha256:109da2c363a1e09432fa2ea2b7dceb6f67d1f91975069fc669e71dd536d654d8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f02a7d95f6cb55234c18abb2f3a67c0a306f262d68ef9b79e11b501a08555b93
+oid sha256:bda65e490958bfe3fe01157ed131eb2354f8fc19536842d27c998ecf29d48991
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537ea638b6cb2eeeba0fa5565c11e75e59cd64d0fdb026e5c722db4638703a11
+oid sha256:bd4e176911da501e895b0ef3a999c4edb2696e1292f30c2ee1775cc16ef16bff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3968,
+  "epoch": 0.5952,
   "eval_steps": 62,
-  "global_step": 124,
+  "global_step": 186,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -234,6 +234,112 @@
       "eval_samples_per_second": 5.47,
       "eval_steps_per_second": 0.356,
       "step": 124
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 70.47568521829318,
+      "learning_rate": 4.786223277909738e-07,
+      "logits/generated": -2.4682154655456543,
+      "logits/real": -2.564629554748535,
+      "logps/generated": -114.67634582519531,
+      "logps/real": -131.61488342285156,
+      "loss": 0.7435,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/generated": 0.9963735342025757,
+      "rewards/margins": 0.43854427337646484,
+      "rewards/real": 1.4349180459976196,
+      "step": 130
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 73.46355856068281,
+      "learning_rate": 4.7268408551068883e-07,
+      "logits/generated": -2.59525728225708,
+      "logits/real": -2.6275722980499268,
+      "logps/generated": -116.23558044433594,
+      "logps/real": -126.39945220947266,
+      "loss": 0.7297,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/generated": 1.0241186618804932,
+      "rewards/margins": 0.5995591878890991,
+      "rewards/real": 1.6236778497695923,
+      "step": 140
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 66.15478984380387,
+      "learning_rate": 4.667458432304038e-07,
+      "logits/generated": -2.5851664543151855,
+      "logits/real": -2.584568977355957,
+      "logps/generated": -115.7433853149414,
+      "logps/real": -126.77409362792969,
+      "loss": 0.7703,
+      "rewards/accuracies": 0.6875,
+      "rewards/generated": 1.2251970767974854,
+      "rewards/margins": 0.4628323018550873,
+      "rewards/real": 1.6880295276641846,
+      "step": 150
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 63.89907025375523,
+      "learning_rate": 4.6080760095011875e-07,
+      "logits/generated": -2.606046438217163,
+      "logits/real": -2.6311333179473877,
+      "logps/generated": -135.02236938476562,
+      "logps/real": -124.39349365234375,
+      "loss": 0.7752,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/generated": 0.7536696195602417,
+      "rewards/margins": 0.8498827815055847,
+      "rewards/real": 1.6035524606704712,
+      "step": 160
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 77.16459067147474,
+      "learning_rate": 4.548693586698337e-07,
+      "logits/generated": -2.3408329486846924,
+      "logits/real": -2.348755121231079,
+      "logps/generated": -111.637939453125,
+      "logps/real": -126.47406005859375,
+      "loss": 0.7802,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/generated": 1.1328538656234741,
+      "rewards/margins": 0.37310591340065,
+      "rewards/real": 1.5059595108032227,
+      "step": 170
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 71.90278136552813,
+      "learning_rate": 4.4893111638954866e-07,
+      "logits/generated": -2.3571982383728027,
+      "logits/real": -2.394517660140991,
+      "logps/generated": -125.56034088134766,
+      "logps/real": -134.2845001220703,
+      "loss": 0.8028,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/generated": 0.9942463040351868,
+      "rewards/margins": 0.24001729488372803,
+      "rewards/real": 1.2342634201049805,
+      "step": 180
+    },
+    {
+      "epoch": 0.5952,
+      "eval_logits/generated": -2.410170316696167,
+      "eval_logits/real": -2.3984007835388184,
+      "eval_logps/generated": -108.79092407226562,
+      "eval_logps/real": -121.71672821044922,
+      "eval_loss": 0.7025200724601746,
+      "eval_rewards/accuracies": 0.6538461446762085,
+      "eval_rewards/generated": 1.2524622678756714,
+      "eval_rewards/margins": 0.4672794044017792,
+      "eval_rewards/real": 1.7197418212890625,
+      "eval_runtime": 36.467,
+      "eval_samples_per_second": 5.484,
+      "eval_steps_per_second": 0.356,
+      "step": 186
     }
   ],
   "logging_steps": 10,