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:bb1a588afeaef8602b67bf0583e6c43af95fbe402a4121f1ea454e804b79fd01
+oid sha256:27279ad98cffcc02979981b8ace48485c567bf19e52ceea14a4dfe739509a438
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01141e8750d30fb63ee970f837374f68644b4bba18b3bb1709965837ca091faf
+oid sha256:636c673f407f3a999553ffaa0c217cef7ea264607fd9b6b387cfb280d7132b10
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dacf26b3729f76f3909fd906769c9d833cf5b11043ea752bec18fd16c5c1873
+oid sha256:44f9f1c4337e0621d656f470fb5437bb2a87d9fb336dbcdc8024d82eaa799879
 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": 1.5113346576690674,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 1.238615664845173,
+  "best_metric": 1.4970587491989136,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 1.3114754098360657,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,13 +245,27 @@
       "eval_samples_per_second": 43.698,
       "eval_steps_per_second": 5.467,
       "step": 1700
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002,
+      "loss": 1.4882,
+      "step": 1800
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 1.4970587491989136,
+      "eval_runtime": 143.4845,
+      "eval_samples_per_second": 43.726,
+      "eval_steps_per_second": 5.471,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0134801452620186e+17,
+  "total_flos": 1.0730188018325914e+17,
   "trial_name": null,
   "trial_params": null
 }