Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc4da44b40e37fc5e3ee8f65ff5dd70ff15326de197b4ce8505ffaea6defc27
+oid sha256:8277758814792b287230784976d9b02c595e2627cec92cac7e3bcafc6622425e
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4965753246bd88fbbe033ee8162cc32b86a3f93ea3926b0ab5e46c6fed7cb92
+oid sha256:f0bf0d8bf8bfabc9ac7d3776eaf4d34402fb0f4597d52ed3fc442dfbcb890114
 size 151032837

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6135dea6869e11c78000d3b6bc11b1b1ade2c0fc5925996274588326a90a2389
+oid sha256:f464edcf4d7dbfc76ed7a7f5bc57357aae01042f47f660bbd2fdc1fc35daadc9
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593f43b0c83adb27a2db37a6418c2ef12a213bbc2a02f2dc881de6846a69a931
+oid sha256:f55ebe991e4838deda9ff3044672335e03697b65b3fe0753cca61998e974ee51
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0949488878250122,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.9151183970856103,
+  "best_metric": 1.0865594148635864,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.9879781420765026,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,13 +567,27 @@
       "eval_samples_per_second": 18.46,
       "eval_steps_per_second": 2.31,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.0685,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.0865594148635864,
+      "eval_runtime": 340.2766,
+      "eval_samples_per_second": 18.438,
+      "eval_steps_per_second": 2.307,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2969094154866883e+18,
+  "total_flos": 1.3292894134103962e+18,
   "trial_name": null,
   "trial_params": null
 }