Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b12a489a5ba6bc052a42b0114486dbb4496c118fa30634ac624849000e02696
+oid sha256:4d60bd3a747fa9fc35e1b40ecba1e1e759508975933f96537fb33b7adb712ded
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:739dbfd0b4439ee9cba2ff31d2b210bbc48440f3423615c3940088111bff5c9f
+oid sha256:cd2da69e2be1e23fe1b1f90953b73f0db8d46cdd18979e746f383f46d76730a8
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728a8ed7ae1358e13d655e3713af360a7485c55ba9e86c8d5822cb07a30b4a27
+oid sha256:9454c9535ad3811e6becd57363e61aef16e6c76875f30d1bdcd4191265ac8ce1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
+oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1822831630706787,
-  "best_model_checkpoint": "./outputs/checkpoint-2700",
-  "epoch": 1.9672131147540983,
+  "best_metric": 2.1763219833374023,
+  "best_model_checkpoint": "./outputs/checkpoint-2800",
+  "epoch": 2.040072859744991,
   "eval_steps": 100,
-  "global_step": 2700,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,13 +385,27 @@
       "eval_samples_per_second": 30.667,
       "eval_steps_per_second": 3.837,
       "step": 2700
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002,
+      "loss": 2.136,
+      "step": 2800
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 2.1763219833374023,
+      "eval_runtime": 204.7219,
+      "eval_samples_per_second": 30.646,
+      "eval_steps_per_second": 3.834,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.69362929814528e+16,
+  "total_flos": 7.971491799484416e+16,
   "trial_name": null,
   "trial_params": null
 }