Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25eb17ce11fb398cce6778e4ac621d162219ae794e46996d3c20bc8b6c854ba5
+oid sha256:7b934623644b2cad72bce18be279967285a692175ebd40ccea73ffe3ed34434f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c4359e0cceadf1107c1fce7e6fc86cc1f309e271eae87aaade1a54b18c067ce
+oid sha256:bc16809c7607f921c1b36704dd4b322eed592cf003c38877592000a5dfcef12e
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283cc7a9be29db0e394f81d7a7a23f335322c5acf210c4dd3b7aae445887d966
+oid sha256:9a82d713e666f36b9ace8a6054cfde823b8feae9a07812ff4e3a4e51f579dbc1
 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": 1.8730626106262207,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.5568181818181817,
+  "best_metric": 1.8645176887512207,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 2.6988636363636362,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,20 @@
       "eval_samples_per_second": 18.951,
       "eval_steps_per_second": 2.375,
       "step": 1800
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0002,
+      "loss": 1.9905,
+      "step": 1900
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 1.8645176887512207,
+      "eval_runtime": 78.5688,
+      "eval_samples_per_second": 18.99,
+      "eval_steps_per_second": 2.38,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.483734889084928e+16,
+  "total_flos": 5.78668418399232e+16,
   "trial_name": null,
   "trial_params": null
 }