Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46762863cb27113f8102c7e5db6a74f6bd4f9d7d9ea67ef227534a67db0dfc78
+oid sha256:1a4009e19ac3f932b12f74b5e5961fb8a1a2da79ef0beb6278bcbe4110281f58
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23db9e3c685c63ebcf4ab8df3f44ba8258f060b4c72f3f8c38afc6e232473504
+oid sha256:c2cdc3d74d2f035f1f3fcaf7445452a3b282c680da8a9098675ce7b6aef4afd7
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4483e6e763a148fd12b5c6250a4686f2858f0c1fd20bfcb3ddd7d995d5334420
+oid sha256:5460bfda360ec6bf006c4e70c03c4e6dd92ee461733554c5eae970f8ca47273c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0210af706e59904c9e8511c5591f24d4a3cc098e12e8fadc4fbcd0318e5ffb7
+oid sha256:75b4b746e7e71a283788a34656838ee1f277007f7a1a22835377cbaf8957d3ae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032,
+  "epoch": 0.0064,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 4.99208e-05,
       "loss": 1.2281,
       "step": 500
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 3.655383348464966,
+      "learning_rate": 4.9840800000000006e-05,
+      "loss": 0.7566,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 4871663124480000.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null