Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8da66a9292141d41a6c48606ed339406a31277522edcf0302aa38aa658f2e9e
+oid sha256:9c30702ff64fa0aba4932e7eadebfb764d6f331c6aba79bc38dd329b15590ba2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6e16c15bc4b1df3cf9e6fe1a2e38058b03a4f63c25e10991bd06af6c213d0c8
+oid sha256:fb2bac883db20ffc2f90dfc94691883c4010a3f4f90dc3d9b417e465fc0af4e5
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34caa8055744af1af91499eaae75425a5f72db08ebfbc7b0e342b4b8e68e6533
+oid sha256:3be9ba5208bb0b7f62289ba0a40fc9a2f25e8400d6b589d90ca0f5299037cd9d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a00f8130c8c43ba3b86ef986c4fb4241ebc0a44808b15806e2c7f948b3aa8ef4
+oid sha256:f69ad02ad549d13e9ab8b866040bb435de5088d2062ba8ddaadf1f207253684e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2468827930174564,
+  "epoch": 1.3507896924355778,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -99,6 +99,13 @@
       "learning_rate": 1.1692989747852592e-05,
       "loss": 0.3737,
       "step": 6000
+    },
+    {
+      "epoch": 1.3507896924355778,
+      "grad_norm": 1.103445053100586,
+      "learning_rate": 1.1000277085065116e-05,
+      "loss": 0.3626,
+      "step": 6500
     }
   ],
   "logging_steps": 500,
@@ -118,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7306885728829440.0,
+  "total_flos": 7915843619389440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null