Training in progress, step 124, checkpoint

last-checkpoint/global_step124/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8232dc29225a0415e93846f907f121d4883923a2454ac5f24439b1ddaec48ed6
+size 14483467880

last-checkpoint/global_step124/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:eb12c0ff2edb4f0e32ab5b430273aac19e4f909138fcbd89050eaf4325785680
+size 14483467880

last-checkpoint/global_step124/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed8017e9fc3ce74c24dab1205b495fefc3f0cc3a8ec990382dd6a9944b9d1ae
+size 14483467880

last-checkpoint/global_step124/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09aca282ac37c9412a45b2216a419897f820e1673f8ed512018453639b823f45
+size 14483467880

last-checkpoint/global_step124/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66045da7ecfe0e7cb3640c641a4309cae5379c4f301e3c72c1c4a8efe9529782
+size 150629

last-checkpoint/global_step124/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16584df5949a6bb6166bd5286273f4e9b5d86cb9d794005e8298925747917133
+size 150629

last-checkpoint/global_step124/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92af64c22beb18e2a8e224a2437108f2d2d47e27436c3f19c6da4a5c9f96186
+size 150629

last-checkpoint/global_step124/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bb4a2c24916b82c832b2cebf4eb467a11ffa7c9e5514cfa4a382e45b22fe20
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step62
+global_step124

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1313c056599e2844cb7a30e3753cb3fcc1f3fe95c952235ad20b9801ba0f3cfa
+oid sha256:e5ef837fbded3b18cd0a4c60904eea5a7736290649d3272b2d4d747062f78dca
 size 4943162336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebdb8fc2bc7fe59280c4c3f36cc96d0c80b52f8a18ec1e3bbeb0c24ebd84bfca
+oid sha256:94825f39a3c46a97f26e600562154fe1141d122c3aed77b1c8207909e2d39dd3
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7538f12ff8c566bca31f4b0fdf4ac9e9afef563611a613f69cb433a4aeed2596
+oid sha256:ccc54b0a6d0a78d822a62f65c8269ae1cd3e47b5d8ee2bbc91a50cad768ab180
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a1dc8b9f546123ce9b44c28828ae71d9d0ecd6f59c6b7b8337c73cb2e24c49
+oid sha256:a82e580e4e92d21ee2fca0348b8c83585fc265a3bdec704f0dbfaf6f2f800587
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8b225b0323772b66570a16b5c7e6446dc3c9ee076597906a2c90e3c0a383bf
+oid sha256:b2f5b0e26d51388f8180f8023bedbf0f066c7e40bd40eba6f2df3d9d9be582f4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c036a8d528905f7018266618c8bebe4add10c2778ef432fd0116369fa622d815
+oid sha256:14c4a2665fddc1defbf2e5e1c0f3875ebfe701d33e843d7bd93ecde03037e001
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93d88429d97654e76d10b1ba4c36f29a47e210c65a03efdc136f04af8282797
+oid sha256:f02a7d95f6cb55234c18abb2f3a67c0a306f262d68ef9b79e11b501a08555b93
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7a6860338b2857ca387402b84af60aa023d3c6c998b782fb5dcd5a6ae91d2d2
+oid sha256:537ea638b6cb2eeeba0fa5565c11e75e59cd64d0fdb026e5c722db4638703a11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1984,
+  "epoch": 0.3968,
   "eval_steps": 62,
-  "global_step": 62,
+  "global_step": 124,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,112 @@
       "eval_samples_per_second": 7.273,
       "eval_steps_per_second": 0.473,
       "step": 62
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 111.31786558317472,
+      "learning_rate": 3.7234042553191484e-07,
+      "logits/generated": -2.4125685691833496,
+      "logits/real": -2.412478446960449,
+      "logps/generated": -122.41896057128906,
+      "logps/real": -142.01275634765625,
+      "loss": 0.7703,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/generated": 1.1598608493804932,
+      "rewards/margins": 0.22506161034107208,
+      "rewards/real": 1.3849226236343384,
+      "step": 70
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 108.77845029282479,
+      "learning_rate": 4.25531914893617e-07,
+      "logits/generated": -2.425182819366455,
+      "logits/real": -2.4704861640930176,
+      "logps/generated": -111.57796478271484,
+      "logps/real": -133.41946411132812,
+      "loss": 0.7575,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/generated": 1.273758888244629,
+      "rewards/margins": 0.2473028153181076,
+      "rewards/real": 1.521061658859253,
+      "step": 80
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 87.55111605760202,
+      "learning_rate": 4.787234042553192e-07,
+      "logits/generated": -2.457540988922119,
+      "logits/real": -2.5106961727142334,
+      "logps/generated": -118.1611099243164,
+      "logps/real": -128.29928588867188,
+      "loss": 0.6781,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/generated": 0.9840036630630493,
+      "rewards/margins": 0.5047105550765991,
+      "rewards/real": 1.4887142181396484,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 86.71987338916492,
+      "learning_rate": 4.96437054631829e-07,
+      "logits/generated": -2.4262959957122803,
+      "logits/real": -2.446533679962158,
+      "logps/generated": -118.33076477050781,
+      "logps/real": -132.8785400390625,
+      "loss": 0.7601,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/generated": 1.1130377054214478,
+      "rewards/margins": 0.3733757734298706,
+      "rewards/real": 1.4864133596420288,
+      "step": 100
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 85.8458816841653,
+      "learning_rate": 4.904988123515439e-07,
+      "logits/generated": -2.3812742233276367,
+      "logits/real": -2.4494009017944336,
+      "logps/generated": -113.8266372680664,
+      "logps/real": -131.19769287109375,
+      "loss": 0.7051,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/generated": 0.42378121614456177,
+      "rewards/margins": 0.6939576268196106,
+      "rewards/real": 1.1177388429641724,
+      "step": 110
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 71.18315494374211,
+      "learning_rate": 4.845605700712589e-07,
+      "logits/generated": -2.4884400367736816,
+      "logits/real": -2.6123955249786377,
+      "logps/generated": -122.7501220703125,
+      "logps/real": -125.4404067993164,
+      "loss": 0.7524,
+      "rewards/accuracies": 0.5625,
+      "rewards/generated": 1.1129395961761475,
+      "rewards/margins": 0.42210373282432556,
+      "rewards/real": 1.5350432395935059,
+      "step": 120
+    },
+    {
+      "epoch": 0.3968,
+      "eval_logits/generated": -2.5561394691467285,
+      "eval_logits/real": -2.586364269256592,
+      "eval_logps/generated": -108.77558898925781,
+      "eval_logps/real": -121.60958099365234,
+      "eval_loss": 0.7001773715019226,
+      "eval_rewards/accuracies": 0.692307710647583,
+      "eval_rewards/generated": 1.2539945840835571,
+      "eval_rewards/margins": 0.47646236419677734,
+      "eval_rewards/real": 1.7304571866989136,
+      "eval_runtime": 36.5599,
+      "eval_samples_per_second": 5.47,
+      "eval_steps_per_second": 0.356,
+      "step": 124
     }
   ],
   "logging_steps": 10,