Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9415856e807b29df4993d2b93aca936596036cd8ea77478081e28c5b1693b642
+oid sha256:15fc5b65988dba9a92214885439409a56e1a12adf4b7a814f334349a6f059b72
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5250b12447318c0f90fbb87ee5bfada24895af5f76810a4e55372ceeb9068f
+oid sha256:0a16e11d8fd6c2ba6c7095d563911bce83b0e9473899f5f7c51df3652f230a47
 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 sha256:74206ba2619c9d016ba1c129d7d0bc686d1e7317df183cf2d559f7293b5ce953
+oid sha256:10613e0e6a8bbd05857ec6a1df443a776230ca43f27f89f8af0bb353f93e15b8
 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": 1.1691604322527017e-05,
       "loss": 0.3736,
       "step": 6000
+    },
+    {
+      "epoch": 1.3507896924355778,
+      "grad_norm": 1.1009119749069214,
+      "learning_rate": 1.099889165973954e-05,
+      "loss": 0.3624,
+      "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