Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ea492b6727c6cb028ddcdc53091e1278fb7e8394e4a45c30253dcaaacafab7
+oid sha256:b7b1496ffdef11b567879c4bf2aa6fd9233ebe5b03088c68bd79c90b335bf6df
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85aa6dd64a908f65a1fae28ba6332cf484afa48ed3ff53fca11d7989c5091425
+oid sha256:b89c268d6b8f6599e593d26bc65dbe928aac2e7c93a8c7c50bddb0b6e5364f09
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb4544647d6a00fc4ffbc73361735b21576f69e4073f6c9a9b39d281b1a43f1
+oid sha256:a4ddea7539d4460e1c607301073358fb3ad37c911d0ee5ed22a47ad23df2f9e9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004178720668595307,
+  "epoch": 0.008357441337190614,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 8.911,
       "eval_steps_per_second": 4.455,
       "step": 10
+    },
+    {
+      "epoch": 0.0048216007714561235,
+      "grad_norm": 2.331204414367676,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 7.4394,
+      "step": 15
+    },
+    {
+      "epoch": 0.006428801028608165,
+      "grad_norm": 3.3225786685943604,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 7.0552,
+      "step": 20
+    },
+    {
+      "epoch": 0.006428801028608165,
+      "eval_loss": 1.8020565509796143,
+      "eval_runtime": 147.1652,
+      "eval_samples_per_second": 8.902,
+      "eval_steps_per_second": 4.451,
+      "step": 20
+    },
+    {
+      "epoch": 0.008036001285760206,
+      "grad_norm": 4.083289623260498,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 6.9482,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5063729511137280.0,
+  "total_flos": 1.027009929019392e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null