Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a449235f3756d3813974ce7f6502c955cc5547260baa9444e160f6b6bf3a5df
+oid sha256:2d734e6db78f60fbbbccb113593aad2dacb6d4ef24adf3f2d2f765c04c3543ac
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61e967797bb87cf1a55bf0f69be53afb460e8bfa804153c9a886a3982e31791
+oid sha256:93e652abff809338fab18533d877e6e5d8666ad14769f8c73336a2290bb1d2f4
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f595db6798fd40d1f9625404652b3498dc8e2af6c56836d52a30a167ba08e35f
+oid sha256:ec459b20953804686a31ef9dfbbe457e9e9185e9c16c0990f91f7b84833fdbbf
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ca222bf68a3564a804857106a49feb87b18dba9a0be2082fc90028354b2ec2
+oid sha256:d1809e210db6349fe0ab123cca2b958d44ebb1729354689aaf0244de4c395185
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.335782247380465,
+  "epoch": 4.576659038901602,
   "eval_steps": 500,
-  "global_step": 18000,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,13 @@
       "learning_rate": 0.0008554565165020477,
       "loss": 1.0793,
       "step": 18000
+    },
+    {
+      "epoch": 4.576659038901602,
+      "grad_norm": 0.5131984353065491,
+      "learning_rate": 0.0008474263229743838,
+      "loss": 1.0737,
+      "step": 19000
     }
   ],
   "logging_steps": 1000,
@@ -152,7 +159,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8006571361081754e+17,
+  "total_flos": 1.900695900913664e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null