Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fdbb9af804d15f5110973d90186ec84defa2a665a8482fd83c11a269501602d
+oid sha256:0ae5c81c1c60500c4a5e1dd6dc813ec1e98722c56c518f3879627e98375fc97c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8eed0cff93a66dd9f7dc35bf13769c84be7bd70a4333fe001f86cc9ee212ba
+oid sha256:02ec7dd85fee160cc36f0c35de11d3c1f3f62be09dc2acdbea1436d93df16a1f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca0d52bc1b71ba08e7156c2b45d758a196d38988c6eda67b4df0e9d832fe78c
+oid sha256:e395ce6518143962b06454b53148180fd527e3c70ad1a04b860142fa90882881
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574db7da084c9454e4a06ea3487f7cdcb4dd46faa4038c9a6b4a085fb43bd4b6
+oid sha256:133e76e86cd14a96bc531992fc191ed101dcf5373cd51d0b24c7b1c479a2d7b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
+  "epoch": 0.3333333333333333,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -322,6 +322,41 @@
       "learning_rate": 1.800088888888889e-05,
       "loss": 0.0752,
       "step": 4500
+    },
+    {
+      "epoch": 0.30666666666666664,
+      "grad_norm": 0.22465260326862335,
+      "learning_rate": 1.7956444444444445e-05,
+      "loss": 0.068,
+      "step": 4600
+    },
+    {
+      "epoch": 0.31333333333333335,
+      "grad_norm": 0.0787540078163147,
+      "learning_rate": 1.7912e-05,
+      "loss": 0.077,
+      "step": 4700
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2305675595998764,
+      "learning_rate": 1.786755555555556e-05,
+      "loss": 0.0727,
+      "step": 4800
+    },
+    {
+      "epoch": 0.32666666666666666,
+      "grad_norm": 0.5901878476142883,
+      "learning_rate": 1.7823111111111114e-05,
+      "loss": 0.0717,
+      "step": 4900
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.25235211849212646,
+      "learning_rate": 1.777866666666667e-05,
+      "loss": 0.0669,
+      "step": 5000
     }
   ],
   "logging_steps": 100,
@@ -341,7 +376,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.096124203008e+16,
+  "total_flos": 1.21791578112e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null