Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39160a24f518bb39d40c921eba0157cfc79a62682458140df4d9769685c1b068
+oid sha256:64dbcf237fae8369f55b23d09ee7ff302b4305e95230470792806d4f5beaefce
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d03737474f4b5464ab0a16f2d16328dec5ad6f74a4ba7ae94e673a76a8d897bb
+oid sha256:471516a79c1d1bce2d7f0221facbc27273c25803ac0ef5c4f6871e9e4d64cf86
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc45ac1a35f5f4645973545cd88afbd0064272773488fa12a6e4551c2656024
+oid sha256:a4f26f933cd5a30682ad42a3de6cd890f8aaa49723c34ab9ccdf6d24b30e628d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034840a84c5a8ab5df6df26a6069c2f569beaac573ff6922f4d724159461eb57
+oid sha256:8f7c983c5137eb206988110c9b1855bdf7c8f7f5f71b7c6884401c6871ab55a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3898586866167912,
+  "epoch": 2.493765586034913,
   "eval_steps": 500,
-  "global_step": 11500,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -184,6 +184,13 @@
       "learning_rate": 4.074535882515933e-06,
       "loss": 0.3412,
       "step": 11500
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 0.8355275988578796,
+      "learning_rate": 3.381823219728457e-06,
+      "loss": 0.3168,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -203,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.400481356709888e+16,
+  "total_flos": 1.461377145765888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null