Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0adf0fe6560b2c76deda60c6d5bc9d03c88a7edd9400f740044c30a9366107
+oid sha256:4d26990d34f16257fadd32045ba019dd4f3d688e7119db32f5a1391ac8ae18d3
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1543c7556028514fd72eec4473e4be27f0beda1c9d05b3bb5902f3b8aea8ae
+oid sha256:abd892c2e43c78bce4db6c79ccf128feedd62bd74810d242084ec97410babf60
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05cf802ece851e37f7a2e8e09140678d93619f6c1e72127ae6bb12317798901b
+oid sha256:0dd8bdb1856d17b194a76c19970eb51f58f0ae25d9a87ca8d59468738cbbfe5f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
+oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.157057762145996,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 1.6029143897996359,
+  "best_metric": 2.145142078399658,
+  "best_model_checkpoint": "./outputs/checkpoint-2300",
+  "epoch": 1.6757741347905282,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,13 +315,27 @@
       "eval_samples_per_second": 30.367,
       "eval_steps_per_second": 3.799,
       "step": 2200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 2.1292,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 2.145142078399658,
+      "eval_runtime": 311.6945,
+      "eval_samples_per_second": 20.129,
+      "eval_steps_per_second": 2.518,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.469323520149504e+16,
+  "total_flos": 6.762876423432192e+16,
   "trial_name": null,
   "trial_params": null
 }