Training in progress, step 620, checkpoint

last-checkpoint/global_step620/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3d89c95f89e37f37a87b8e0d63cd51f8eeb84490d139724c37038dafc9c203
+size 14483467880

last-checkpoint/global_step620/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1a351165427eee6ccf8fb35b75b1c2fa9eeffcf04caa9a69ac29237ad504ce
+size 14483467880

last-checkpoint/global_step620/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f66ebabfdb278389ef82f3a6f5a8a735d49f9fdca8e6e092c4ec0268834a0bb
+size 14483467880

last-checkpoint/global_step620/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe93e20eaf14ebf1c121193ab084652ac50265019dd4edcfea5758f0b5da0bb
+size 14483467880

last-checkpoint/global_step620/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353189acafcf58d5522234859c339a3ad63dfa657023ee5b281282dde523627b
+size 150629

last-checkpoint/global_step620/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4fe5daad0262291e805a44bf4b497bf7ed953be022e301762905bce089f127
+size 150629

last-checkpoint/global_step620/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faed547d8f0a20c92d47f05e5fc5be1f95b522a0e4134205ef062d68da5f1c17
+size 150629

last-checkpoint/global_step620/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6ce5170fce92ddc28458c28e80546ad5fc11d1afa4dce327a0105ded5be944
+size 150629

last-checkpoint/latest

@@ -1 +1 @@
-global_step558
+global_step620

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6a528fcebfa81ad94dc98b813bc2eaf50e2093983c66f1cf062eee248c9ce3
+oid sha256:93daaec3380eb160ed1b2b55d7e6a40b3148f5806a93acda8285c13c6ed11ec4
 size 4943162336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87205acf168a99a505e46e06b76a61a6a87e6e70876881ff030e4dad2cd7aa43
+oid sha256:d99f0e63f5427ff1eb28a5e26e8a6cb5f108907e9ec53956cf11addbcacf1c34
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c09c12a0ba4fd95fb32e1df06312c869712e92aa026283345f20f3f5ad8b86a
+oid sha256:6dd3351df120c66885127c540da0c2667724cb06d47ddfb327a851ef7dace34c
 size 4540516344

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3d4793d6c7fda650513b6f3d24fe7afd643475a576b0104a85cb659ed441d3
+oid sha256:b3ea85ce0faf4f25f8f01506659575c6ffa73d2668e6dcf972bea416c2f14cf7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44567105884943a8351ea71e9a71011cceee34a8f2a067be69948ea21390f49
+oid sha256:6df02d244f55294fc3a1bed06a850d7dc043249b3e97a2a1f72408d7e378d44b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3a6f11c1c82a313f717b58d29d20267d0bfc621c79116ac6f752e0c1ba1f50
+oid sha256:dbafb0c52cec706b84eb0e477953ab4950ffc8e931e49bbc7a37cd7d5d929a69
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa97839e10563397740560600a86ccaf5a6fe1e5f41084453cab0f732a05570
+oid sha256:007e6b920b3c7dfd19dd00d30bc01c0cd1682b25270dc31952d9b737d039f1d1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41569355a67e5d54cd2e41fbdb883692602ceaf27587e7a1c779dc0f9f2d51fd
+oid sha256:44a438c4653759e5a86be993ca4420444015d4e70859f1f853dd1fc989248fda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7856,
+  "epoch": 1.984,
   "eval_steps": 62,
-  "global_step": 558,
+  "global_step": 620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -991,6 +991,127 @@
       "eval_samples_per_second": 5.376,
       "eval_steps_per_second": 0.349,
       "step": 558
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 36.45272717171445,
+      "learning_rate": 2.2327790973871732e-07,
+      "logits/generated": -2.4495067596435547,
+      "logits/real": -2.4794678688049316,
+      "logps/generated": -132.83074951171875,
+      "logps/real": -119.1983413696289,
+      "loss": 0.3839,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": 0.6143507957458496,
+      "rewards/margins": 2.7835047245025635,
+      "rewards/real": 3.397855281829834,
+      "step": 560
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 47.41784238396275,
+      "learning_rate": 2.173396674584323e-07,
+      "logits/generated": -2.371821641921997,
+      "logits/real": -2.4102165699005127,
+      "logps/generated": -118.35310363769531,
+      "logps/real": -104.9133529663086,
+      "loss": 0.3493,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": 0.35018137097358704,
+      "rewards/margins": 2.667248487472534,
+      "rewards/real": 3.017429828643799,
+      "step": 570
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 49.63769156744519,
+      "learning_rate": 2.1140142517814726e-07,
+      "logits/generated": -2.4235947132110596,
+      "logits/real": -2.425346851348877,
+      "logps/generated": -111.2136001586914,
+      "logps/real": -107.47050476074219,
+      "loss": 0.3654,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/generated": 0.31659263372421265,
+      "rewards/margins": 2.903308153152466,
+      "rewards/real": 3.219900608062744,
+      "step": 580
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 58.661910753155134,
+      "learning_rate": 2.0546318289786222e-07,
+      "logits/generated": -2.431994676589966,
+      "logits/real": -2.488813638687134,
+      "logps/generated": -129.04559326171875,
+      "logps/real": -119.28230285644531,
+      "loss": 0.4107,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/generated": 0.3402375876903534,
+      "rewards/margins": 2.8488047122955322,
+      "rewards/real": 3.189042091369629,
+      "step": 590
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 21.619481492021077,
+      "learning_rate": 1.9952494061757718e-07,
+      "logits/generated": -2.436246871948242,
+      "logits/real": -2.466956377029419,
+      "logps/generated": -116.15250396728516,
+      "logps/real": -107.74141693115234,
+      "loss": 0.4577,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": 0.5984365344047546,
+      "rewards/margins": 2.591343641281128,
+      "rewards/real": 3.1897804737091064,
+      "step": 600
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 45.346853109328364,
+      "learning_rate": 1.9358669833729216e-07,
+      "logits/generated": -2.4542717933654785,
+      "logits/real": -2.4808132648468018,
+      "logps/generated": -101.80671691894531,
+      "logps/real": -96.19842529296875,
+      "loss": 0.4562,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": 0.5814850330352783,
+      "rewards/margins": 2.2760722637176514,
+      "rewards/real": 2.8575568199157715,
+      "step": 610
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 44.76458950174624,
+      "learning_rate": 1.876484560570071e-07,
+      "logits/generated": -2.506688356399536,
+      "logits/real": -2.5051321983337402,
+      "logps/generated": -109.52842712402344,
+      "logps/real": -100.06086730957031,
+      "loss": 0.3933,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": 0.37385421991348267,
+      "rewards/margins": 2.584712266921997,
+      "rewards/real": 2.958566665649414,
+      "step": 620
+    },
+    {
+      "epoch": 1.984,
+      "eval_logits/generated": -2.432065725326538,
+      "eval_logits/real": -2.426744222640991,
+      "eval_logps/generated": -104.29174041748047,
+      "eval_logps/real": -115.62232971191406,
+      "eval_loss": 0.7168198227882385,
+      "eval_rewards/accuracies": 0.6730769276618958,
+      "eval_rewards/generated": 1.7023800611495972,
+      "eval_rewards/margins": 0.6268020868301392,
+      "eval_rewards/real": 2.3291821479797363,
+      "eval_runtime": 36.5982,
+      "eval_samples_per_second": 5.465,
+      "eval_steps_per_second": 0.355,
+      "step": 620
     }
   ],
   "logging_steps": 10,