Training in progress, step 868, checkpoint

last-checkpoint/global_step868/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d373eee01f46747bf9b3ff262ae05ee14ba3f91aed0df0280fdffd6d261d24b
+size 14483467880

last-checkpoint/global_step868/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:d08bbefd916d1c9390a1329f91eae56d29b4d4d22ffa16b2dbe169c422e8f610
+size 14483467880

last-checkpoint/global_step868/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae39e66019f2289d1d2b61b50b99e0fcdca9934fa72cce6a551f9e5c668e654
+size 14483467880

last-checkpoint/global_step868/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a51fb19e21a2bf0c4de0b2e8f65e08741e16601bd4ca48d8ba8af00262b9488
+size 14483467880

last-checkpoint/global_step868/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d7e9efb2e141e6e9e6255f7d81521dd9a991493c3a2f561a68005b4b12ea86
+size 150629

last-checkpoint/global_step868/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9983f08a72661666879082f9f5064686bc2eebea9fb36b48b9cc020c4b74ca7f
+size 150629

last-checkpoint/global_step868/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f016ebf514bb495af750a075ec720a50234d37eb4d353fd53038f46d22cd2c7e
+size 150629

last-checkpoint/global_step868/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69702c6c7036fa6579f2b4eb2b267656235a93969516e2add91dc8f26ffa8ba
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step806
+global_step868

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01443e5b1be1845b23d068379f502f29cc0d605aa3c723e62099e0363435171
+oid sha256:49ed8f0847a6d218a8d1eccb47868dcceb5eca54475b6157db67d660a1803d1d
 size 4943162336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57856b5dd2475ebf9c4ebc1f56181dd8ea5989ca79593d85e80aac4d34207982
+oid sha256:637ae61efed0ceac33b21a213b84b61d20e3cb817770b79a2eda25413cbb5a3c
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278adea3df02b4ec9199dc8f091dc366d112cc565d81277e1d7cf6feecb8eb02
+oid sha256:5d0d7a867e4f5af4d520757d6e400338df292c54d603ec0f25b0254c5ee9e6f5
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ea574d07a576c8cd612773a5015f4f8303ef6ce35f964bd81b8b489ceed9bd
+oid sha256:8639c02c997d5ec74743bd87a283daff10faa317419bf379edd99c706559f2ce
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231c40114b2d8985fa7545edd47494bc1e9d1e0a8db77f30a4d192048f265712
+oid sha256:211a79d80fe07a9690b74e693f719eafa8303e6798af58a53dd105eb19c8ccc5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d4d2cd69e482e80eb9dbe4006558389d72a76a801f542398022187d536edd47
+oid sha256:319730d0d11be8a12d1633e218e39729160d397a56a34d9ebd2e63d2c81fd68f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d86ba141f647d4a747b93c9fe2e7871e4a119de2b70afdde8f5f8f330a1740
+oid sha256:8e7c1d2c0fa7220ac8b520afb2fc0958467f149187d655695c73de033474c910
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:127121878f3c4f6f6f6fd96373d0f7ed77bb9443425be91537513fdc909d04df
+oid sha256:d0a127df5e8aedd711ac814e5c853ecd07390a0c8ef0dc12756e27ebaa732ecd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5792,
+  "epoch": 2.7776,
   "eval_steps": 62,
-  "global_step": 806,
+  "global_step": 868,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1430,6 +1430,112 @@
       "eval_samples_per_second": 5.423,
       "eval_steps_per_second": 0.353,
       "step": 806
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 49.93127642652704,
+      "learning_rate": 7.482185273159145e-08,
+      "logits/generated": -2.2843379974365234,
+      "logits/real": -2.4402122497558594,
+      "logps/generated": -136.36618041992188,
+      "logps/real": -96.77020263671875,
+      "loss": 0.2065,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -0.5222247838973999,
+      "rewards/margins": 4.2587480545043945,
+      "rewards/real": 3.736523151397705,
+      "step": 810
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 37.58250644609933,
+      "learning_rate": 6.88836104513064e-08,
+      "logits/generated": -2.3502609729766846,
+      "logits/real": -2.4047064781188965,
+      "logps/generated": -141.55758666992188,
+      "logps/real": -115.49945068359375,
+      "loss": 0.2793,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -0.4805728793144226,
+      "rewards/margins": 4.331357002258301,
+      "rewards/real": 3.850783586502075,
+      "step": 820
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 35.86590095950996,
+      "learning_rate": 6.294536817102138e-08,
+      "logits/generated": -2.4404706954956055,
+      "logits/real": -2.3888516426086426,
+      "logps/generated": -119.47889709472656,
+      "logps/real": -102.79316711425781,
+      "loss": 0.2456,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -0.43787437677383423,
+      "rewards/margins": 4.165786266326904,
+      "rewards/real": 3.7279114723205566,
+      "step": 830
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 72.52101185428741,
+      "learning_rate": 5.700712589073634e-08,
+      "logits/generated": -2.3413405418395996,
+      "logits/real": -2.4445858001708984,
+      "logps/generated": -143.9036102294922,
+      "logps/real": -120.9752197265625,
+      "loss": 0.2809,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": 0.0636942982673645,
+      "rewards/margins": 4.376380920410156,
+      "rewards/real": 4.440074920654297,
+      "step": 840
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 47.87386592895277,
+      "learning_rate": 5.10688836104513e-08,
+      "logits/generated": -2.459815740585327,
+      "logits/real": -2.4833953380584717,
+      "logps/generated": -145.05397033691406,
+      "logps/real": -100.8636703491211,
+      "loss": 0.1964,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -0.6957341432571411,
+      "rewards/margins": 4.412557125091553,
+      "rewards/real": 3.716822385787964,
+      "step": 850
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 14.759861860387986,
+      "learning_rate": 4.5130641330166267e-08,
+      "logits/generated": -2.402906656265259,
+      "logits/real": -2.3498435020446777,
+      "logps/generated": -135.8385467529297,
+      "logps/real": -100.04483795166016,
+      "loss": 0.2423,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -0.7252713441848755,
+      "rewards/margins": 4.6403326988220215,
+      "rewards/real": 3.9150619506835938,
+      "step": 860
+    },
+    {
+      "epoch": 2.7776,
+      "eval_logits/generated": -2.3574001789093018,
+      "eval_logits/real": -2.3973894119262695,
+      "eval_logps/generated": -105.71865844726562,
+      "eval_logps/real": -116.01789093017578,
+      "eval_loss": 0.7526271343231201,
+      "eval_rewards/accuracies": 0.5961538553237915,
+      "eval_rewards/generated": 1.5596884489059448,
+      "eval_rewards/margins": 0.7299386262893677,
+      "eval_rewards/real": 2.2896268367767334,
+      "eval_runtime": 37.3402,
+      "eval_samples_per_second": 5.356,
+      "eval_steps_per_second": 0.348,
+      "step": 868
     }
   ],
   "logging_steps": 10,