Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81d4d58688a5108922a14e176aecce09ec8539a8cbaa3af2e246ab5c4f954987
+oid sha256:f1f60e5b2b840b10354b7113d140f3cbb4a4d556867ef6478f22a08f664d3521
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f85bc11bfeea9119152dc29fdb8ef7dd70294e44e930bdffb6208b7e2c7481
+oid sha256:236a382be424a1f131c12a370d4b69e6807a3b2fffdb4db849a1291862f7baa8
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1d98121dec1e10b89cbbf79fb7433fce4fe8fbe36ae0274a84026345108858
+oid sha256:5877e96d88bc486eb083b9ffdaed482a8ee342de0d30ce8efc7818182ef17f26
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6951390504837036,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 1.6701356172561646,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 0.6557377049180327,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,13 +119,27 @@
       "eval_samples_per_second": 43.576,
       "eval_steps_per_second": 5.452,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 1.674,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 1.6701356172561646,
+      "eval_runtime": 144.0222,
+      "eval_samples_per_second": 43.563,
+      "eval_steps_per_second": 5.451,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.770481186612838e+16,
+  "total_flos": 5.365348992702874e+16,
   "trial_name": null,
   "trial_params": null
 }