Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a525271f33029751bd79e6ee02b8f285c8714d8e51fbd2d01f2cbbc6f2587cf
+oid sha256:417f1995b4557cbfec20e2a145867bcf0f7c6b41e77cf3788f8608190c2409fb
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2aa86f6d9ec2adc3adb47645de46597c94342c51105606b5b824aa6946f32b1
+oid sha256:102d524a8da90dd9e3c6d1202281c87537233533e5bedfbe298d692298f87281
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390f4c31f151d1b722c751920ce3c1346c4474b6f2b5548196c30af3030d0e42
+oid sha256:0d9a5e96d5319f578e3676c8a6aaa1d019c2f577ff8abb55dcf5d74b47d9273c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4863215684890747,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 1.3114754098360657,
+  "best_metric": 1.4718947410583496,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 1.384335154826958,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,13 +259,27 @@
       "eval_samples_per_second": 43.628,
       "eval_steps_per_second": 5.459,
       "step": 1800
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002,
+      "loss": 1.4677,
+      "step": 1900
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 1.4718947410583496,
+      "eval_runtime": 143.7145,
+      "eval_samples_per_second": 43.656,
+      "eval_steps_per_second": 5.462,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0731311264781926e+17,
+  "total_flos": 1.1327940508889088e+17,
   "trial_name": null,
   "trial_params": null
 }