Training in progress, step 179, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0352da14b9889a7ab3c77e88e1bf3c4144928efa4e3cc0b0548b0ddd21dff81
+oid sha256:0f1649a48e414b30fa938a4eaa0af8e0bc36876d607459e8923113b96984263f
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:815521070c1931daacd69c70c447014828b03cce6ffb61ca5c7f195a3cda2eef
+oid sha256:38011f5c788a07ff43c63a579288cbddad0558cfb0108186efc471bf2299de99
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:364fccfdcd95be9ec62ffeac9d34c8d74da7e0596253c84c3fe30982d321ed77
+oid sha256:6ad126561e92062035cecad91de5ed48906ed35a99eb18df9acd3e68bd9c878d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.48010973936899864,
+  "epoch": 0.49108367626886146,
   "eval_steps": 500,
-  "global_step": 175,
+  "global_step": 179,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1232,6 +1232,34 @@
       "learning_rate": 0.0001431818181818182,
       "loss": 1.2387,
       "step": 175
+    },
+    {
+      "epoch": 0.4828532235939643,
+      "grad_norm": 0.14522749185562134,
+      "learning_rate": 0.00014242424242424243,
+      "loss": 1.2214,
+      "step": 176
+    },
+    {
+      "epoch": 0.48559670781893005,
+      "grad_norm": 0.14445781707763672,
+      "learning_rate": 0.00014166666666666668,
+      "loss": 1.2424,
+      "step": 177
+    },
+    {
+      "epoch": 0.4883401920438957,
+      "grad_norm": 0.15134842693805695,
+      "learning_rate": 0.00014090909090909093,
+      "loss": 1.2522,
+      "step": 178
+    },
+    {
+      "epoch": 0.49108367626886146,
+      "grad_norm": 0.15704961121082306,
+      "learning_rate": 0.00014015151515151518,
+      "loss": 1.2584,
+      "step": 179
     }
   ],
   "logging_steps": 1,
@@ -1251,7 +1279,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1724788193907098e+17,
+  "total_flos": 2.2233487438710374e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null