Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d53b42c9a65ea8a71fa514cfd812c834fd8f6a88ee20bf277eb09935a229f10
+oid sha256:bd435d4c565278ca4fe642f0569217eae31db204692f8170a78cc060584eb864
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3bdf9f2744ada44e175861929ea0fb1500658841567b8662101a566eac61829
+oid sha256:15f1632c64d76783d8907c3e92a7713d23c2df60b1e1a3079d9b3c7be3413a9f
 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:c8b7a78225852024e3d86de8f9611d84d4cdcf3e30b5b9840972fad85092017b
+oid sha256:a5d59de19a41db12fa634f2104bc781b1687cd88f74eced8badd275d850b3566
 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": 4.0759213078415074e-06,
       "loss": 0.3411,
       "step": 11500
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 0.8265316486358643,
+      "learning_rate": 3.3832086450540318e-06,
+      "loss": 0.317,
+      "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