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:a8392d0284ece174dc5ee1fb6c19d267f0e3a4fafdab7dc8f8071a16dd5c0c03
+oid sha256:0aa8a38a99adbb6b86d95a8e88bae913ce143e94b7424352e70d64006e97f8f7
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9242e058bda8388a7f0463c55cda99769798cfa808e1241ee4add565a25fbe
+oid sha256:cb7f1f3770b40fd29e9fe2d8e8e6cb188fbc7927c7790a397e71ae90d8ab8dc9
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00580629d2b234d79ad597794a5ab43605b7065c826449c360fab80984f94740
+oid sha256:2fcf009a64a304dce1129b0fdc1b80a365b4ef48344321c5dfb03cba1db1c591
 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": 0.9535185098648071,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.5568181818181817,
+  "best_metric": 0.9502108693122864,
+  "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": 12.412,
       "eval_steps_per_second": 1.556,
       "step": 1800
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.0002,
+      "loss": 1.0671,
+      "step": 1900
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 0.9502108693122864,
+      "eval_runtime": 124.6118,
+      "eval_samples_per_second": 11.973,
+      "eval_steps_per_second": 1.501,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.012140847420416e+17,
+  "total_flos": 1.0682272179726336e+17,
   "trial_name": null,
   "trial_params": null
 }