Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4380650dcb89ea554e8e522387212bf4d52c5c83459f83e79d11aeaa75e938f3
+oid sha256:55fb81428939778dab08e7922db21d016e3f504c05107e029c92f5fce46fe882
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6265fff472063a8acba8dfd3c39858c1d92510671c7894dd6142eea88a2418a
+oid sha256:a229809403e9c000da99928a1a77232623f005939cd31324d820e5637351f23b
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b5794f891efa039dc7974b27a227de46156bc8c7ebd7ea9d3d86467b6bab57
+oid sha256:eba198d9667b25aa3e1e3ed428937b84fcb61b09b165df40f8a2db486d218cb8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.095290251916758,
+  "epoch": 1.3691128148959475,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,41 @@
       "learning_rate": 9.574389385212366e-05,
       "loss": 1.1348,
       "step": 2000
+    },
+    {
+      "epoch": 1.1500547645125958,
+      "grad_norm": 2.488781213760376,
+      "learning_rate": 9.493886427336657e-05,
+      "loss": 1.1794,
+      "step": 2100
+    },
+    {
+      "epoch": 1.2048192771084336,
+      "grad_norm": 2.216630697250366,
+      "learning_rate": 9.406815330073244e-05,
+      "loss": 1.1533,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2595837897042717,
+      "grad_norm": 2.5205495357513428,
+      "learning_rate": 9.313303354115677e-05,
+      "loss": 1.1383,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3143483023001095,
+      "grad_norm": 2.7046151161193848,
+      "learning_rate": 9.213487173966623e-05,
+      "loss": 1.1639,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3691128148959475,
+      "grad_norm": 2.2721831798553467,
+      "learning_rate": 9.107512678178223e-05,
+      "loss": 1.1572,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
@@ -166,7 +201,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.642466312538358e+17,
+  "total_flos": 1.2070042691739648e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null