Training in progress, step 17500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adfa46e3ddfd088ddcff8e2b4d5d2e22b5262134efabf88908d983013cadef2
+oid sha256:ac4ff6911227b7e5523118974a2c2a3be5b88a4c49daff13003ae3ea0ac78c1c
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c58829c4bcf80e72ccd1f5def21e54e28ca040dc00cc84a75d3765eef60d58
+oid sha256:18064219000301c81565cb3c031763e67a81df224d8e65ec24d5bb84e5afec68
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a515644a1536d58bc151d4772fbcb30c6719059de1dca0ac69481684fdd622ee
+oid sha256:3112ea078250afbcb19bb0d83740928f379be034d54b299e4e0dc7a0f9a5620d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8030e4de81bed9438f1213c20e98e00469ffeac6ae1e0ae6de34e5da948dd505
+oid sha256:7892bd04827a170151f1a5ac37c3514d334483f0ffc2116bdeee6de8b682972b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.608962553713935,
+  "epoch": 2.685696746470227,
   "eval_steps": 500,
-  "global_step": 17000,
+  "global_step": 17500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,13 +231,19 @@
       "learning_rate": 0.00047839165131982814,
       "loss": 0.524,
       "step": 17000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.0004630448127685697,
+      "loss": 0.526,
+      "step": 17500
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 9011746539307008.0,
+  "total_flos": 9276745786589184.0,
   "trial_name": null,
   "trial_params": null
 }