Training in progress, step 30000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1162f3dd69f25f8696965e77a13ee78f76a56faa207df54198db0aa2c1ff8d34
+oid sha256:4eb840687881657e048d395c385a9084b7bcca678b6abb14165c472542383ceb
 size 18915040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a392000d9293e83d945e935d13a886a99f359ba416db00324a34f83ac689a60
+oid sha256:df5f5ee2b56d6c0f93fb801be312fc1bd48ab0eacd78bb34294fb243c2b7397a
 size 37990394

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:052cb623d333c55cb6aa932d620c4240d6da273a0db3bf72bfdbcc2be7693707
+oid sha256:cbfd5efb5880d038e40ef818b6a478489100d8537842fb87344a0d7f88275ee0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c007ea3613e729374f49a992d59f46f0bb1762290dd86d4c3105289d354272e2
+oid sha256:71d106c12a183d47d2349d6d228d20595c1cad95f8d19fec2a8622032de302f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7267124980015406,
+  "epoch": 0.8720549976018488,
   "eval_steps": 500,
-  "global_step": 25000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,13 +307,73 @@
       "learning_rate": 7.617450650796032e-05,
       "loss": 3.1865,
       "step": 25000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.601617768363678e-05,
+      "loss": 3.2224,
+      "step": 25500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.58548099572581e-05,
+      "loss": 3.1192,
+      "step": 26000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.569041694439229e-05,
+      "loss": 3.1802,
+      "step": 26500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 7.552301251586894e-05,
+      "loss": 3.1781,
+      "step": 27000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.5352610796609e-05,
+      "loss": 3.1921,
+      "step": 27500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 7.517922616443289e-05,
+      "loss": 3.1896,
+      "step": 28000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 7.500287324884736e-05,
+      "loss": 3.1911,
+      "step": 28500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 7.482356692981116e-05,
+      "loss": 3.1367,
+      "step": 29000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.464132233647945e-05,
+      "loss": 3.1416,
+      "step": 29500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 7.445615484592736e-05,
+      "loss": 3.1682,
+      "step": 30000
     }
   ],
   "logging_steps": 500,
   "max_steps": 172005,
   "num_train_epochs": 5,
   "save_steps": 5000,
-  "total_flos": 8.566811394048e+17,
+  "total_flos": 1.02801736728576e+18,
   "trial_name": null,
   "trial_params": null
 }