Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14661dd62079aafb6d62a7aa44c4d471eb5869e867f5786f5fec60b869a05884
+oid sha256:c8ca12b21105befb0813b9fbc6b96b81367649b0c611adf60525a49f857a1fd2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:878fdf213c549c70e6e58544d458a41774b313b275ecc5a35d91394253732e8c
+oid sha256:69c7418c25c6a3c167fc48418e2dd598449951bd5e68404aa0f44f0722e5e6fd
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193cf8763e811dd3e32b43e244a311e62a543ef8398d3b107ff52fb9af797950
+oid sha256:8142adb50de721c312198118970172331afa1dd03733dddae1b8e58019f13418
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7746f1d3dca9d005c3f4add9ea23143cbd616cc0c9a441906d9f1036f61b2904
+oid sha256:795b978d5d5017aeee81eb81d35587849afe22455c4e21ab42718587ec12da55
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6625103906899419,
+  "epoch": 1.766417290108063,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,13 @@
       "learning_rate": 8.920753671377114e-06,
       "loss": 0.3635,
       "step": 8000
+    },
+    {
+      "epoch": 1.766417290108063,
+      "grad_norm": 0.8015578985214233,
+      "learning_rate": 8.228041008589638e-06,
+      "loss": 0.3549,
+      "step": 8500
     }
   ],
   "logging_steps": 500,
@@ -146,7 +153,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9742717291069440.0,
+  "total_flos": 1.035167518162944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null