Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb976cf7898c7af69200f2113a29b7785b019b770d22039687f7f5c4a96ed7fa
+oid sha256:9128c30f8a3b26280560a868afe89cca76661efd2a33ceb3c658eddf190de8bb
 size 72673016

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76358ba8b0d5790094202317f145647c6a255e57fe759204944b37c5cf4cd2e5
+oid sha256:8cc10cf500af2626b5d2b4f076a07c678e565cf08a810b0e33e8a52555d5cc40
 size 36892116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c28d755d296a8737ed6670f14159a70f28b726a19cbe726d0f62337231c234c4
+oid sha256:3ece262c534d1b7d1db5a2ce2fd578c733d0164261019904322133288edf8c12
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26645e1de4f1ee60c55cf09276f6d2fe8bef6c9276d818480910d55b43b1d8a1
+oid sha256:34561662f8e54ce65c36d4fcca2b1c512c5ba02e6fc1a025cbd92eb43f288458
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.023631723225257587,
+  "epoch": 0.028358067870309103,
   "eval_steps": 1000,
-  "global_step": 125,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,13 +757,163 @@
       "learning_rate": 0.00015524193548387098,
       "loss": 1.8046,
       "step": 125
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00015483870967741937,
+      "loss": 1.8889,
+      "step": 126
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00015443548387096776,
+      "loss": 1.9183,
+      "step": 127
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00015403225806451615,
+      "loss": 1.6254,
+      "step": 128
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00015362903225806454,
+      "loss": 1.8339,
+      "step": 129
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001532258064516129,
+      "loss": 1.94,
+      "step": 130
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00015282258064516131,
+      "loss": 1.9235,
+      "step": 131
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00015241935483870968,
+      "loss": 1.78,
+      "step": 132
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001520161290322581,
+      "loss": 1.7514,
+      "step": 133
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015161290322580646,
+      "loss": 1.8281,
+      "step": 134
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015120967741935485,
+      "loss": 1.8109,
+      "step": 135
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015080645161290323,
+      "loss": 1.9297,
+      "step": 136
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015040322580645162,
+      "loss": 1.7198,
+      "step": 137
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7704,
+      "step": 138
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014959677419354838,
+      "loss": 1.8345,
+      "step": 139
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001491935483870968,
+      "loss": 1.7694,
+      "step": 140
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014879032258064516,
+      "loss": 1.8196,
+      "step": 141
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014838709677419355,
+      "loss": 1.8625,
+      "step": 142
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014798387096774193,
+      "loss": 1.9182,
+      "step": 143
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014758064516129032,
+      "loss": 1.4297,
+      "step": 144
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014717741935483871,
+      "loss": 1.929,
+      "step": 145
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001467741935483871,
+      "loss": 1.9118,
+      "step": 146
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001463709677419355,
+      "loss": 2.0179,
+      "step": 147
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014596774193548388,
+      "loss": 1.8938,
+      "step": 148
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014556451612903224,
+      "loss": 1.8689,
+      "step": 149
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00014516129032258066,
+      "loss": 1.6793,
+      "step": 150
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 6054706182193152.0,
+  "total_flos": 7280753121067008.0,
   "trial_name": null,
   "trial_params": null
 }