Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4146169c596c8a46b6a1c46d56fdd08f1dada7f00ec225e8ea9e4d71472f70
+oid sha256:7ab1af3989a3cb0ef17441134c6d9115d239c28d341121ec54ddc157bc80ca31
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181ff8f655987df2051473c2aa6d62574ed5c4c93c498f6bacbda1bb9807c208
+oid sha256:ee7fd58185a25f322d89f31ab1205c29d56ebbe0608d01fbd4ed1810b096d21d
 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:a09ad69a3f61f9d3d9f02f2a0456c9d35adee50f06a3734fa06d48a8a6546239
+oid sha256:0999afe033f75d8bd9448190d8bb949c5c3397cd764ae214dd958ddb75be8cfe
 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": 8.92213909670269e-06,
       "loss": 0.3639,
       "step": 8000
+    },
+    {
+      "epoch": 1.766417290108063,
+      "grad_norm": 0.8235663771629333,
+      "learning_rate": 8.229426433915213e-06,
+      "loss": 0.355,
+      "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