Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dea2c89bef20be615fcce396baaeae2863c872440d067f0890f1feafdcce916
+oid sha256:0a92b715fe8596794c3cc9c282406baeeedb154cb6fde102a455a0463d4c773b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00bacac910cb93e9a685d60ee478a59d636259c2cedb034834a5373e41f18165
+oid sha256:af64cfff14825e0676e4add08f661b8ec13b6e0224a2d8a49379393e538563a5
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce122efa58437e9eb4167be3235ff668c46393aa7e777fe0c234b56b42a65288
+oid sha256:4ef6f9afaee6b3c66bd6603d6f0a1ae70b2f238fe9e271cbda545439817d0f6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddbe69375e1ef0ed25b67e47b35f8d767c1d1535d6aa10c8d75b5ca27ee0eabb
+oid sha256:0f0b2d0c48b553cb761ed72f66ac5dc41e40acbef7cd18d2608a3a45cba61a88
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10390689941812137,
+  "epoch": 0.20781379883624274,
   "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": 1.9310058187863676e-05,
       "loss": 0.8022,
       "step": 500
+    },
+    {
+      "epoch": 0.20781379883624274,
+      "grad_norm": 0.8622527122497559,
+      "learning_rate": 1.86173455250762e-05,
+      "loss": 0.5316,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 608957890560000.0,
+  "total_flos": 1217915781120000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null