Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8712cb5970d7b705c14498f8792473ad178666286d127651626282b1405d4c3b
+oid sha256:8f14b8f7b9087016403701eec6a7862b2894ae7a0353d88bb7236d699972d717
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb758e8f8c145d44477aae47ef63297cebdc559314998b8fff2296780971935
+oid sha256:d676101575c5d7e889c442d5c94a5fa466ccc42648cf9c9ab6990cb06ec0b6e2
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1fa92a659ce7b24b7bee26ef1c5b22af6de24bc71dca8f081d8a4d5484f829f
+oid sha256:d2b52d82f73e570b1698336d070d85ea4c32ca359687f3058f1f92bb220326cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1f06ceb303ff0ec410ef313e8a8843d875c3abbfab44ea08bf6f1574965321
+oid sha256:b9120c40acc17c5b623355fbfb43e37d51967de752e9eedd3525b8954bac5054
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20781379883624274,
+  "epoch": 0.41562759767248547,
   "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": 1.862011637572735e-05,
       "loss": 0.5079,
       "step": 500
+    },
+    {
+      "epoch": 0.41562759767248547,
+      "grad_norm": 0.8360931873321533,
+      "learning_rate": 1.72346910501524e-05,
+      "loss": 0.4047,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -33,7 +40,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1217915781120000.0,
+  "total_flos": 2435831562240000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null