Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed24e154de5566609e7cab9ff283141640a81cad49bf66869e6612084d097189
+oid sha256:a8392d0284ece174dc5ee1fb6c19d267f0e3a4fafdab7dc8f8071a16dd5c0c03
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de879bb2e19f835b3e839a36fd87550256c10817dfb87d979207d61c87c69463
+oid sha256:fe9242e058bda8388a7f0463c55cda99769798cfa808e1241ee4add565a25fbe
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d31a0dc339240aaf93f937650507de96ef2bf626940e68c39c22a3f81eb87d
+oid sha256:00580629d2b234d79ad597794a5ab43605b7065c826449c360fab80984f94740
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9569491744041443,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.4147727272727275,
+  "best_metric": 0.9535185098648071,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 2.5568181818181817,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 12.416,
       "eval_steps_per_second": 1.556,
       "step": 1700
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.0002,
+      "loss": 1.0627,
+      "step": 1800
+    },
+    {
+      "epoch": 2.56,
+      "eval_loss": 0.9535185098648071,
+      "eval_runtime": 120.202,
+      "eval_samples_per_second": 12.412,
+      "eval_steps_per_second": 1.556,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.559346065532928e+16,
+  "total_flos": 1.012140847420416e+17,
   "trial_name": null,
   "trial_params": null
 }