Training in progress, step 248, checkpoint

last-checkpoint/global_step248/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b08794cdafca4a2405e677b4792eeb1c4002d519acd0473d1c10e1aa565d567
+size 14483467880

last-checkpoint/global_step248/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:d75109bb6240b53ff9e71157b60bdbb1c7d170e52510b3c30529adc92679d162
+size 14483467880

last-checkpoint/global_step248/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfede4f8422dc2803797167730273a781c8af94b515f7db405e151010938e66
+size 14483467880

last-checkpoint/global_step248/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1c917c53e44b8ef80c8cec62dc0938ce8ae27a5e900bb3f07ad29001135cdb
+size 14483467880

last-checkpoint/global_step248/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12a4cac7a1cb413656ed2b84b87dac9dd2b5c9457a0a6b56887bb9e066fcf64
+size 150629

last-checkpoint/global_step248/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d41d0da714359fbf813c0a5eb00cf5143b1943361a731e52e40897f07173521
+size 150629

last-checkpoint/global_step248/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c98308f6801467dcbda81513e0a255846ff8d2d0d1ca1b0b62562138abe897d
+size 150629

last-checkpoint/global_step248/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41447a8be1f5647c7283a2d60028ccc22a8c7b8d8d6373e6bc59d2818a31c0dc
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step186
+global_step248

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86ddf4ca1c25503e71e7f08d6596d0773148bd1af28bc8f2c1a7165ea636a1d
+oid sha256:aa70bb996156bbded8548797ca1f4ee1575a045cddb2a9cc7df4062722aeb4c9
 size 4943162336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94333f558ff69c31fb1fb843a840e7ebfda4e3534d6404c0dfb993ceaede38e8
+oid sha256:222edc16474f6eae34b4b7b14958aa7eed9b3da9527638f098fa5434ee77df8f
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc022c32b0063f7be7c5541e0cb999e9e9d168f2aa00002bed63bd368a24152
+oid sha256:3bb1df50fb89ebcc0fba450c7354cf3779333974ca8c122499541771dad338b0
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ca27603f7c4a4d9a980223e1a102922ac31561acfa7da4f28042e4e8b3528b
+oid sha256:24e15ff45212eaf6c8decc16dc22c41c4ce080a39ad2deb8865f5b3888d4efb2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57f658c3d9b6de611da50021823095fc4067036fb9a4b34655cc2e34fbf5c2b
+oid sha256:0766646143405ae7d8761387ef336c681649fc67c22c6b6fd693a70b83271308
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:109da2c363a1e09432fa2ea2b7dceb6f67d1f91975069fc669e71dd536d654d8
+oid sha256:705dd3e24877a6ecb456032edc7da887e9e915c7d513964cecbec240a9a9513b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda65e490958bfe3fe01157ed131eb2354f8fc19536842d27c998ecf29d48991
+oid sha256:4bd4f44e10fc7beca1269b92451cc181ceccf15015c11f280a598b7ca4e6b5fa
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4e176911da501e895b0ef3a999c4edb2696e1292f30c2ee1775cc16ef16bff
+oid sha256:c67f7ec77e804e39476b9d19eb7621ae6832d1f14416eb0651e4d7ceac525a87
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5952,
+  "epoch": 0.7936,
   "eval_steps": 62,
-  "global_step": 186,
+  "global_step": 248,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -340,6 +340,112 @@
       "eval_samples_per_second": 5.484,
       "eval_steps_per_second": 0.356,
       "step": 186
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 86.7511219785863,
+      "learning_rate": 4.429928741092636e-07,
+      "logits/generated": -2.4148917198181152,
+      "logits/real": -2.3717541694641113,
+      "logps/generated": -118.5252685546875,
+      "logps/real": -148.78070068359375,
+      "loss": 0.7774,
+      "rewards/accuracies": 0.75,
+      "rewards/generated": 0.8947796821594238,
+      "rewards/margins": 0.7275075912475586,
+      "rewards/real": 1.6222871541976929,
+      "step": 190
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 81.51532186606975,
+      "learning_rate": 4.3705463182897863e-07,
+      "logits/generated": -2.333613872528076,
+      "logits/real": -2.317903757095337,
+      "logps/generated": -106.9345703125,
+      "logps/real": -122.63179779052734,
+      "loss": 0.7231,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/generated": 1.007331132888794,
+      "rewards/margins": 0.8109349012374878,
+      "rewards/real": 1.8182659149169922,
+      "step": 200
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 66.81550093382229,
+      "learning_rate": 4.311163895486936e-07,
+      "logits/generated": -2.3513429164886475,
+      "logits/real": -2.4845714569091797,
+      "logps/generated": -115.06642150878906,
+      "logps/real": -125.45219421386719,
+      "loss": 0.7643,
+      "rewards/accuracies": 0.625,
+      "rewards/generated": 1.3189352750778198,
+      "rewards/margins": 0.4965497851371765,
+      "rewards/real": 1.8154850006103516,
+      "step": 210
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 69.67950191082039,
+      "learning_rate": 4.251781472684085e-07,
+      "logits/generated": -2.458786725997925,
+      "logits/real": -2.4684672355651855,
+      "logps/generated": -104.95294189453125,
+      "logps/real": -110.86625671386719,
+      "loss": 0.7933,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/generated": 1.5485458374023438,
+      "rewards/margins": 0.44912296533584595,
+      "rewards/real": 1.9976688623428345,
+      "step": 220
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 67.77084563505426,
+      "learning_rate": 4.192399049881235e-07,
+      "logits/generated": -2.4709246158599854,
+      "logits/real": -2.4637975692749023,
+      "logps/generated": -109.6999282836914,
+      "logps/real": -118.01756286621094,
+      "loss": 0.7679,
+      "rewards/accuracies": 0.8125,
+      "rewards/generated": 1.0844991207122803,
+      "rewards/margins": 0.8938215374946594,
+      "rewards/real": 1.978320837020874,
+      "step": 230
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 72.48546532520147,
+      "learning_rate": 4.1330166270783846e-07,
+      "logits/generated": -2.4811666011810303,
+      "logits/real": -2.499788284301758,
+      "logps/generated": -121.445068359375,
+      "logps/real": -134.60311889648438,
+      "loss": 0.7502,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/generated": 1.3976621627807617,
+      "rewards/margins": 0.5193124413490295,
+      "rewards/real": 1.916974425315857,
+      "step": 240
+    },
+    {
+      "epoch": 0.7936,
+      "eval_logits/generated": -2.5031919479370117,
+      "eval_logits/real": -2.5135350227355957,
+      "eval_logps/generated": -111.80171966552734,
+      "eval_logps/real": -123.52568054199219,
+      "eval_loss": 0.7087541222572327,
+      "eval_rewards/accuracies": 0.6346153616905212,
+      "eval_rewards/generated": 0.9513813257217407,
+      "eval_rewards/margins": 0.5874653458595276,
+      "eval_rewards/real": 1.538846731185913,
+      "eval_runtime": 37.1383,
+      "eval_samples_per_second": 5.385,
+      "eval_steps_per_second": 0.35,
+      "step": 248
     }
   ],
   "logging_steps": 10,