Training in progress, step 930, checkpoint

last-checkpoint/global_step930/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa08966d8dc9427ed0e7f7f3eb8bf1cefb83008b10e5650f1b7c8a015a0de7d
+size 14483467880

last-checkpoint/global_step930/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:be4f83c84e72c5c3b8824eac0171131d4329604ef8b4d0a45227dd3b341167f6
+size 14483467880

last-checkpoint/global_step930/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:c93613ce7b583d30d3d45a000aa57bf80d18f49aaaf1b0160f73e928c30aa305
+size 14483467880

last-checkpoint/global_step930/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:bcfc3330efb4caf704d765f9f6a54b55802d457dcca98b2249a21f1308300cc3
+size 14483467880

last-checkpoint/global_step930/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8235ea59a76df970fdd89d217227959a0e0a18cafb57843ddba09fc46890ba3d
+size 150629

last-checkpoint/global_step930/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc24f1425ef33b883cbf0586835f648175e6ddd007079dacbbfdbcaf553ab2f
+size 150629

last-checkpoint/global_step930/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a2755526c30550de59ba9ee2290d7a539afaf4085a71abf57ddae6603971dd
+size 150629

last-checkpoint/global_step930/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862ace45acbeb0cbd76349c80aff0d460a525b3d142d9e5b729f11f573c28cc3
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step868
+global_step930

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ed8f0847a6d218a8d1eccb47868dcceb5eca54475b6157db67d660a1803d1d
+oid sha256:94bfb89fd02254d0d7d2cdb822bf9e53d6192c903b5c2ead0592f671b52bcf7a
 size 4943162336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:637ae61efed0ceac33b21a213b84b61d20e3cb817770b79a2eda25413cbb5a3c
+oid sha256:8fc9727b3a71f7c7369f878f68474786432cbe6fa1dea710d3ff96fa9d70e4e0
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0d7a867e4f5af4d520757d6e400338df292c54d603ec0f25b0254c5ee9e6f5
+oid sha256:8b410ea095f6d34f670a5401486f9ca473f3f3ad7131eac5a39a6e40e73a6d18
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8639c02c997d5ec74743bd87a283daff10faa317419bf379edd99c706559f2ce
+oid sha256:e5b5b0934b8613429f71d38c4aaf1cf68b50eb415214b938124e65c4e50faae1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:211a79d80fe07a9690b74e693f719eafa8303e6798af58a53dd105eb19c8ccc5
+oid sha256:19f63bfbf9ef9efae26be62fb115c8fa6adfa6333f3074d8511b5eeab88f0f1e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319730d0d11be8a12d1633e218e39729160d397a56a34d9ebd2e63d2c81fd68f
+oid sha256:ba2a5ec9c47d3c544c4e610213c6d14c67721b556bd12896b90b14fd54cf1901
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7c1d2c0fa7220ac8b520afb2fc0958467f149187d655695c73de033474c910
+oid sha256:7e5fd0b1afc88ca5e581b87462a6a56c9a82154f0d69fe336f7b445bad77242b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a127df5e8aedd711ac814e5c853ecd07390a0c8ef0dc12756e27ebaa732ecd
+oid sha256:98ace375a7a3e380a16715316d6e5e36d9cb62649995c07cc349fb85673d36ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7776,
+  "epoch": 2.976,
   "eval_steps": 62,
-  "global_step": 868,
+  "global_step": 930,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1536,6 +1536,127 @@
       "eval_samples_per_second": 5.356,
       "eval_steps_per_second": 0.348,
       "step": 868
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 39.33798985134705,
+      "learning_rate": 3.919239904988123e-08,
+      "logits/generated": -2.3367316722869873,
+      "logits/real": -2.405890941619873,
+      "logps/generated": -134.0688018798828,
+      "logps/real": -103.1637191772461,
+      "loss": 0.2581,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -0.24620242416858673,
+      "rewards/margins": 4.148200035095215,
+      "rewards/real": 3.9019978046417236,
+      "step": 870
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 19.24691526629623,
+      "learning_rate": 3.32541567695962e-08,
+      "logits/generated": -2.3322081565856934,
+      "logits/real": -2.3643596172332764,
+      "logps/generated": -131.92562866210938,
+      "logps/real": -100.34136199951172,
+      "loss": 0.2497,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -0.7228564620018005,
+      "rewards/margins": 4.272365093231201,
+      "rewards/real": 3.549508571624756,
+      "step": 880
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 74.32934828209018,
+      "learning_rate": 2.7315914489311164e-08,
+      "logits/generated": -2.411259174346924,
+      "logits/real": -2.4403157234191895,
+      "logps/generated": -153.52029418945312,
+      "logps/real": -101.80616760253906,
+      "loss": 0.2214,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -0.7813536524772644,
+      "rewards/margins": 4.41187047958374,
+      "rewards/real": 3.630516767501831,
+      "step": 890
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 17.231794888700385,
+      "learning_rate": 2.1377672209026125e-08,
+      "logits/generated": -2.440458297729492,
+      "logits/real": -2.4329943656921387,
+      "logps/generated": -131.6967010498047,
+      "logps/real": -100.85757446289062,
+      "loss": 0.1728,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -1.0743391513824463,
+      "rewards/margins": 4.5941972732543945,
+      "rewards/real": 3.5198585987091064,
+      "step": 900
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 31.31269522304366,
+      "learning_rate": 1.5439429928741092e-08,
+      "logits/generated": -2.288120985031128,
+      "logits/real": -2.4024569988250732,
+      "logps/generated": -126.20759582519531,
+      "logps/real": -93.2852554321289,
+      "loss": 0.2286,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -0.7462027072906494,
+      "rewards/margins": 4.080456256866455,
+      "rewards/real": 3.3342537879943848,
+      "step": 910
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 39.94010884942353,
+      "learning_rate": 9.501187648456057e-09,
+      "logits/generated": -2.390730381011963,
+      "logits/real": -2.414212226867676,
+      "logps/generated": -127.1091537475586,
+      "logps/real": -113.78387451171875,
+      "loss": 0.2001,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -0.6455323696136475,
+      "rewards/margins": 4.345826148986816,
+      "rewards/real": 3.700294017791748,
+      "step": 920
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 24.96632528956892,
+      "learning_rate": 3.562945368171021e-09,
+      "logits/generated": -2.4350810050964355,
+      "logits/real": -2.3702778816223145,
+      "logps/generated": -130.21060180664062,
+      "logps/real": -103.36898040771484,
+      "loss": 0.2881,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -0.7739312648773193,
+      "rewards/margins": 4.571539878845215,
+      "rewards/real": 3.7976088523864746,
+      "step": 930
+    },
+    {
+      "epoch": 2.976,
+      "eval_logits/generated": -2.3562779426574707,
+      "eval_logits/real": -2.3975794315338135,
+      "eval_logps/generated": -106.50991821289062,
+      "eval_logps/real": -116.46751403808594,
+      "eval_loss": 0.7523060441017151,
+      "eval_rewards/accuracies": 0.6153846383094788,
+      "eval_rewards/generated": 1.4805629253387451,
+      "eval_rewards/margins": 0.7641012668609619,
+      "eval_rewards/real": 2.244664430618286,
+      "eval_runtime": 37.8351,
+      "eval_samples_per_second": 5.286,
+      "eval_steps_per_second": 0.344,
+      "step": 930
     }
   ],
   "logging_steps": 10,