Training in progress, step 434, checkpoint

last-checkpoint/global_step434/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f4fae62919166e360e09e6aa85ee751fcb46becc1a02c358919a60be9f4199d
+size 14483467880

last-checkpoint/global_step434/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f505e2b7f5ed7cf2d7fab017c0df883273ed433a9872269450921d4c415fae2
+size 14483467880

last-checkpoint/global_step434/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:f8c1b727e8fcaaf0083d8576b52c91aad9425d3698ef5ae69f7ec28ef1100773
+size 14483467880

last-checkpoint/global_step434/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cfd32231e5485b455599fef3515380b9bc80b978d4028a2f606eb1b9cd57e86
+size 14483467880

last-checkpoint/global_step434/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70bc7b4d8283b95c393450bd2d11588759a3d0aded76b3d684c998355f039038
+size 150629

last-checkpoint/global_step434/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a08d5b63905ae091a847a740d3a3302da5b1108998ce5d3ee21ab9f47df9b3
+size 150629

last-checkpoint/global_step434/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964d24390710093dbd186b0722c22f1574698ed4568bcb8b71a80a3c29ffcec0
+size 150629

last-checkpoint/global_step434/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9746b2b724054e060040d0c5c1e4f100518769ae60d8efe1fcd63cd052b1414
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step310
+global_step434

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871e22c99857224236f3beac6d7dfa370009645a8341a6c82c6fba0894599a39
+oid sha256:958716f2df1897ad484fdf7bd07ec6d719787775a371768ed3c7437e70de2232
 size 4943162336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1473ff03a94f69178942e4433588e696b2de4cca8b2b7b1cb2ead8a0165daf01
+oid sha256:39c4675562a0a001a6edf29b49c1472e3f7ec329ca9c5cde5f458022e6dd467c
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9b9be22821de3ead61e2beff759327749b217de661f05659dd746c2ce92a84
+oid sha256:c6f60fa901b8ebbd827b9acb1118f03a3eade9e3e3fc451be3522245d27b7d06
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a44fde7a8ca235658f035c0812d344f55779640520411739b17e214177e846
+oid sha256:fe3f96a2fff0ebd8dbcc2b4789c9dd47a218358381d8dc0c22453d73cc18c13a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2caad91201b0df46e56af9eecef567ed2037350c38fdc81837724a4727d0b050
+oid sha256:03c2e37b3b994a43a2c3a96dca7647061b052e8930abe99d16ea118bb9a4e2bc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e988587366c84fd1b4fc5931610543c6da84cf501cd98c78745fd102dd5024
+oid sha256:dd2fb470636af306fe33bfa071a70c5e89bbc147a17ff3351e6d952861610b64
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55af3bb04c01d99df727583b8b7a09241b4e47d58ff1b9cf5532d3fa0d878b52
+oid sha256:42f403a555728d319355f2901e7ccab38b27c2ffdef1825aa77e363c48d96a77
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1f3ea23a20057969bd2d32326dcc0e5b037b552ec94e8e00a566c43a06b809
+oid sha256:ffb2c72a1d7475512f08b2573f4f5ec2d68a3f42a3844b97c4df08ba0cc7a09b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.992,
+  "epoch": 1.3888,
   "eval_steps": 62,
-  "global_step": 310,
+  "global_step": 434,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,6 +567,218 @@
       "eval_samples_per_second": 5.519,
       "eval_steps_per_second": 0.359,
       "step": 310
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 23.478068074273793,
+      "learning_rate": 3.6579572446555817e-07,
+      "logits/generated": -2.4226808547973633,
+      "logits/real": -2.4831509590148926,
+      "logps/generated": -105.56974792480469,
+      "logps/real": -120.84535217285156,
+      "loss": 0.4414,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": 0.5887820720672607,
+      "rewards/margins": 2.0551419258117676,
+      "rewards/real": 2.6439242362976074,
+      "step": 320
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 53.84789861907458,
+      "learning_rate": 3.598574821852731e-07,
+      "logits/generated": -2.562809944152832,
+      "logits/real": -2.54683256149292,
+      "logps/generated": -110.83638000488281,
+      "logps/real": -106.26161193847656,
+      "loss": 0.3126,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": 0.8259130716323853,
+      "rewards/margins": 2.4829070568084717,
+      "rewards/real": 3.3088200092315674,
+      "step": 330
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 25.743224152634117,
+      "learning_rate": 3.5391923990498813e-07,
+      "logits/generated": -2.567718982696533,
+      "logits/real": -2.5672295093536377,
+      "logps/generated": -133.78305053710938,
+      "logps/real": -108.94974517822266,
+      "loss": 0.3081,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": 0.4089571535587311,
+      "rewards/margins": 3.111121416091919,
+      "rewards/real": 3.520078659057617,
+      "step": 340
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 27.156393795142105,
+      "learning_rate": 3.479809976247031e-07,
+      "logits/generated": -2.552985668182373,
+      "logits/real": -2.639397144317627,
+      "logps/generated": -118.40696716308594,
+      "logps/real": -106.28694152832031,
+      "loss": 0.3855,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": 0.319620817899704,
+      "rewards/margins": 2.3786392211914062,
+      "rewards/real": 2.6982600688934326,
+      "step": 350
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 17.27004888873941,
+      "learning_rate": 3.42042755344418e-07,
+      "logits/generated": -2.629342555999756,
+      "logits/real": -2.6742465496063232,
+      "logps/generated": -119.6379165649414,
+      "logps/real": -97.76652526855469,
+      "loss": 0.2743,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": 0.05346187204122543,
+      "rewards/margins": 2.755115270614624,
+      "rewards/real": 2.808577537536621,
+      "step": 360
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 41.22537338864181,
+      "learning_rate": 3.36104513064133e-07,
+      "logits/generated": -2.5502161979675293,
+      "logits/real": -2.5699377059936523,
+      "logps/generated": -116.44935607910156,
+      "logps/real": -108.02735900878906,
+      "loss": 0.3246,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": 0.30488744378089905,
+      "rewards/margins": 2.962125301361084,
+      "rewards/real": 3.26701283454895,
+      "step": 370
+    },
+    {
+      "epoch": 1.1904,
+      "eval_logits/generated": -2.5670902729034424,
+      "eval_logits/real": -2.5847625732421875,
+      "eval_logps/generated": -104.2799072265625,
+      "eval_logps/real": -115.69155883789062,
+      "eval_loss": 0.7214540839195251,
+      "eval_rewards/accuracies": 0.6730769276618958,
+      "eval_rewards/generated": 1.7035623788833618,
+      "eval_rewards/margins": 0.618696928024292,
+      "eval_rewards/real": 2.3222594261169434,
+      "eval_runtime": 36.7301,
+      "eval_samples_per_second": 5.445,
+      "eval_steps_per_second": 0.354,
+      "step": 372
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 42.19482089195438,
+      "learning_rate": 3.3016627078384796e-07,
+      "logits/generated": -2.6010684967041016,
+      "logits/real": -2.563749313354492,
+      "logps/generated": -127.38044738769531,
+      "logps/real": -122.81330871582031,
+      "loss": 0.3494,
+      "rewards/accuracies": 0.875,
+      "rewards/generated": 0.5199904441833496,
+      "rewards/margins": 2.884294033050537,
+      "rewards/real": 3.4042842388153076,
+      "step": 380
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 53.916948193274834,
+      "learning_rate": 3.2422802850356297e-07,
+      "logits/generated": -2.5801901817321777,
+      "logits/real": -2.5469508171081543,
+      "logps/generated": -126.4742202758789,
+      "logps/real": -122.43565368652344,
+      "loss": 0.3655,
+      "rewards/accuracies": 0.875,
+      "rewards/generated": 0.2614704668521881,
+      "rewards/margins": 2.877016544342041,
+      "rewards/real": 3.1384871006011963,
+      "step": 390
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 37.850375132000444,
+      "learning_rate": 3.182897862232779e-07,
+      "logits/generated": -2.5271100997924805,
+      "logits/real": -2.5569581985473633,
+      "logps/generated": -135.80126953125,
+      "logps/real": -107.57261657714844,
+      "loss": 0.3173,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": -0.10970146954059601,
+      "rewards/margins": 2.853787422180176,
+      "rewards/real": 2.7440860271453857,
+      "step": 400
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 41.572987230872016,
+      "learning_rate": 3.1235154394299283e-07,
+      "logits/generated": -2.5878734588623047,
+      "logits/real": -2.721327066421509,
+      "logps/generated": -112.33902740478516,
+      "logps/real": -97.48545837402344,
+      "loss": 0.3206,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": 0.2867007851600647,
+      "rewards/margins": 2.679920196533203,
+      "rewards/real": 2.966620922088623,
+      "step": 410
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 30.741827558770616,
+      "learning_rate": 3.0641330166270784e-07,
+      "logits/generated": -2.4893412590026855,
+      "logits/real": -2.570223331451416,
+      "logps/generated": -110.69290924072266,
+      "logps/real": -98.38088989257812,
+      "loss": 0.3303,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": 0.0641188770532608,
+      "rewards/margins": 2.817840099334717,
+      "rewards/real": 2.8819591999053955,
+      "step": 420
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 37.05106236999541,
+      "learning_rate": 3.004750593824228e-07,
+      "logits/generated": -2.5790863037109375,
+      "logits/real": -2.562358856201172,
+      "logps/generated": -122.13496398925781,
+      "logps/real": -102.71966552734375,
+      "loss": 0.3153,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -0.3958076536655426,
+      "rewards/margins": 3.1295769214630127,
+      "rewards/real": 2.733769655227661,
+      "step": 430
+    },
+    {
+      "epoch": 1.3888,
+      "eval_logits/generated": -2.499913454055786,
+      "eval_logits/real": -2.525455951690674,
+      "eval_logps/generated": -104.29454040527344,
+      "eval_logps/real": -115.43984985351562,
+      "eval_loss": 0.7150266170501709,
+      "eval_rewards/accuracies": 0.6538461446762085,
+      "eval_rewards/generated": 1.7021007537841797,
+      "eval_rewards/margins": 0.6453297138214111,
+      "eval_rewards/real": 2.3474302291870117,
+      "eval_runtime": 37.3175,
+      "eval_samples_per_second": 5.359,
+      "eval_steps_per_second": 0.348,
+      "step": 434
     }
   ],
   "logging_steps": 10,