Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4276fed1397b0954e680466cea0d481a57ba70180922712a76d50d5e20fe99e1
+oid sha256:5b383873c26832688de8d1c4e2cec99e2c080f55c2a733ed72ff54f5da6db032
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a608bdfb5b1ad4d3a40b4584028b29e5ea5ad8c9d7bfb2b815d85d5126f4b2b
+oid sha256:48a6854066078859b7042e8ef23c5376c7c9fab782496447aa1d2049a5072914
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923547af05cdd3afc057dbec6a47ce6d9a810c418671b3571637a299d286d7be
+oid sha256:455992e41bd4da0ca76dc0d3b1d29b2d2a3f92f6143e641ebfdcc3ceccc55b08
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9241eff24b3925a44e89d3db66c6446b322e7c397558e0282e0355814c8466fd
+oid sha256:79b2a778b609ad3bfe944c34ea5338f4a67422eb690449bc00076aa57ca39206
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8440761203192142,
+  "epoch": 0.9208103130755064,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,13 +73,19 @@
       "learning_rate": 0.0008312154696132597,
       "loss": 0.611,
       "step": 5500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0008158686310620012,
+      "loss": 0.617,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 2914518023798784.0,
+  "total_flos": 3179276193497088.0,
   "trial_name": null,
   "trial_params": null
 }