Training in progress, step 26000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f8bbdcef942ca91b5ec7bbbd735231f5e4d26584c5cdee0e481501fe23e48b
+oid sha256:c2eb2e99816ec43430cbc064844c5e9639d5777774741cf5128e00d44cc22f84
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f30063e10b99a88358cb2b15c6445572352ad0fdb9ca22aac6f16a615cc3216
+oid sha256:ffff2b04f3ac17f12a961b31f194814499e7fd990021cd2b459a7cd25f837f54
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbcd414e2ebe010dcb7c52553aab3fd4fa6d365b6f63593edeab1858ed2ed198
+oid sha256:2f52f95da495bb27845cab982f10d0992545e1a1f3379ad63ed77c13e8413544
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797fe0fbbc0deae3aec7fbd325c4b3b26250213d429ef253b6bc3ac068bea992
+oid sha256:34f762ade12141f21b1db11036bc2604582ab540ca56d64f7190f6e92cb5741c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7,
+  "epoch": 1.7333333333333334,
   "eval_steps": 500,
-  "global_step": 25500,
+  "global_step": 26000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1800,6 +1800,41 @@
       "learning_rate": 8.670222222222223e-06,
       "loss": 0.0596,
       "step": 25500
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 0.20626091957092285,
+      "learning_rate": 8.625777777777779e-06,
+      "loss": 0.0523,
+      "step": 25600
+    },
+    {
+      "epoch": 1.7133333333333334,
+      "grad_norm": 0.1952398121356964,
+      "learning_rate": 8.581333333333334e-06,
+      "loss": 0.0508,
+      "step": 25700
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.15694676339626312,
+      "learning_rate": 8.53688888888889e-06,
+      "loss": 0.052,
+      "step": 25800
+    },
+    {
+      "epoch": 1.7266666666666666,
+      "grad_norm": 0.07521438598632812,
+      "learning_rate": 8.492444444444446e-06,
+      "loss": 0.0597,
+      "step": 25900
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.07147266715765,
+      "learning_rate": 8.448000000000001e-06,
+      "loss": 0.0555,
+      "step": 26000
     }
   ],
   "logging_steps": 100,
@@ -1819,7 +1854,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.211370483712e+16,
+  "total_flos": 6.333162061824e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null