Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4ff6911227b7e5523118974a2c2a3be5b88a4c49daff13003ae3ea0ac78c1c
+oid sha256:7af7e2acb2501348b70ac013aa2673c03c7f95852e6ea918387411294656a265
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18064219000301c81565cb3c031763e67a81df224d8e65ec24d5bb84e5afec68
+oid sha256:2ef55aa9dcb7937da2cf2e092478ad70091d50840f4c23049425933f0eedb04a
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3112ea078250afbcb19bb0d83740928f379be034d54b299e4e0dc7a0f9a5620d
+oid sha256:5a4843546ebf0691d234f88402f68d1d26480a3213229d5852134c943fbad945
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7892bd04827a170151f1a5ac37c3514d334483f0ffc2116bdeee6de8b682972b
+oid sha256:9a4b08f241048c40d93df455e0e834330823c94d21c421d6e45fbc0abf4da2bf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.685696746470227,
+  "epoch": 2.7624309392265194,
   "eval_steps": 500,
-  "global_step": 17500,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -237,13 +237,19 @@
       "learning_rate": 0.0004630448127685697,
       "loss": 0.526,
       "step": 17500
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 0.00044772866789441376,
+      "loss": 0.5323,
+      "step": 18000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 9276745786589184.0,
+  "total_flos": 9541994570317824.0,
   "trial_name": null,
   "trial_params": null
 }