Training in progress, step 11500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:893983e61e005312c4a5a5937ac7d9e97a84f157f2d2506651c26610d9fc5649
+oid sha256:3d53b42c9a65ea8a71fa514cfd812c834fd8f6a88ee20bf277eb09935a229f10
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c6f9fb1ab37c26c8e9cd8f06ff85c9304df7bb97167c11edaec7366d9b2dd7
+oid sha256:a3bdf9f2744ada44e175861929ea0fb1500658841567b8662101a566eac61829
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81366beb45812d30c24b5a5034071dc5850a14e0029b0be5806b5186ffb17322
+oid sha256:4bc45ac1a35f5f4645973545cd88afbd0064272773488fa12a6e4551c2656024
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976d1f52844e987390213cc75aaff01e7bbae8d7552dcf3147571e784e111d4d
+oid sha256:c8b7a78225852024e3d86de8f9611d84d4cdcf3e30b5b9840972fad85092017b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.28595178719867,
+  "epoch": 2.3898586866167912,
   "eval_steps": 500,
-  "global_step": 11000,
+  "global_step": 11500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -177,6 +177,13 @@
       "learning_rate": 4.767248545303408e-06,
       "loss": 0.3387,
       "step": 11000
+    },
+    {
+      "epoch": 2.3898586866167912,
+      "grad_norm": 1.4450799226760864,
+      "learning_rate": 4.0759213078415074e-06,
+      "loss": 0.3411,
+      "step": 11500
     }
   ],
   "logging_steps": 500,
@@ -196,7 +203,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.339585567653888e+16,
+  "total_flos": 1.400481356709888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null