Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c69f833487fb8e0851ca646981b19736b3c1a1f034585ffbe6eb66f15a4dcd2
+oid sha256:86088744fc73991dbad542cb575e003e003845f7733294f33cccef3a4ea00bab
 size 167832240

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7bcbd7c15af307086c8612a9346710f4f085869c374516e635760305db5cc77
+oid sha256:16a17ae578843264458af1825dd54e9b6c49feedf8389be152d73b055998d99d
 size 335945362

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385bd3c889817bb109fe4830882aab3bfcbb5e4eccc5e7fa6a2cc353228178a3
+oid sha256:4cc3acd79ef21a0c8cfd24a04c27cc1b761922190e7386ae99698fbbdb092058
 size 167939550

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859214dc387eb3e62419c68b424697c31e86f60684ce969a4432863354d30aa8
+oid sha256:337059d54254bc9389c938dc292312990ce226dd122bd2ed92af370c28fd9326
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04329687676175443,
+  "epoch": 0.04870898635697373,
   "eval_steps": 500,
-  "global_step": 24,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -368,6 +368,51 @@
       "rewards/margins": 1.7218996286392212,
       "rewards/rejected": -6.634063243865967,
       "step": 24
+    },
+    {
+      "epoch": 0.045100913293494194,
+      "grad_norm": 2.239922523498535,
+      "learning_rate": 2.7103137257858868e-05,
+      "logits/chosen": -0.9918060302734375,
+      "logits/rejected": -1.0055713653564453,
+      "logps/chosen": -81.97212219238281,
+      "logps/rejected": -112.09403228759766,
+      "loss": 0.2746,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": -3.760244846343994,
+      "rewards/margins": 2.3255343437194824,
+      "rewards/rejected": -6.085779190063477,
+      "step": 25
+    },
+    {
+      "epoch": 0.04690494982523396,
+      "grad_norm": 2.042022228240967,
+      "learning_rate": 1.9098300562505266e-05,
+      "logits/chosen": -0.9954603314399719,
+      "logits/rejected": -0.9743874073028564,
+      "logps/chosen": -86.01747131347656,
+      "logps/rejected": -118.19400787353516,
+      "loss": 0.3832,
+      "rewards/accuracies": 0.828125,
+      "rewards/chosen": -4.391570091247559,
+      "rewards/margins": 2.4328856468200684,
+      "rewards/rejected": -6.824456214904785,
+      "step": 26
+    },
+    {
+      "epoch": 0.04870898635697373,
+      "grad_norm": 2.6501646041870117,
+      "learning_rate": 1.2369331995613665e-05,
+      "logits/chosen": -0.9255884885787964,
+      "logits/rejected": -0.9290853142738342,
+      "logps/chosen": -88.18702697753906,
+      "logps/rejected": -117.44279479980469,
+      "loss": 0.4081,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -4.232594013214111,
+      "rewards/margins": 2.055999279022217,
+      "rewards/rejected": -6.28859281539917,
+      "step": 27
     }
   ],
   "logging_steps": 1,