Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b370b9d957291373c1f893567324d282072390b78bc55ac09aa959bb3d95daf
+oid sha256:f858914822aed8ad7a6e6cbac56e0f2135171987b473ab07759f0f86ae930d8b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c27778262824218357c3807cbf8925b9ca2eb150ce7d5bd10de91c264c3e202
+oid sha256:8f694b43e613a1edb1eb9626d4dbd11a83fa86fe1be69c8adeec2debd4cb4047
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0082b9ee265cb0c6910d3944f6a738794d996da2e7f7ac5ed1f97dde094437
+oid sha256:0bcd094c31c6302ab0f6b8a0d552c64675298946a65fbc2f7cfe61f1f9a1ad9d
 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": 0.0021232289412437223,
+  "epoch": 0.004246457882487445,
   "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": 13.95,
       "eval_steps_per_second": 6.975,
       "step": 10
+    },
+    {
+      "epoch": 0.0024498795475889103,
+      "grad_norm": 1.6047385931015015,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.9002,
+      "step": 15
+    },
+    {
+      "epoch": 0.0032665060634518802,
+      "grad_norm": 1.2641571760177612,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.8778,
+      "step": 20
+    },
+    {
+      "epoch": 0.0032665060634518802,
+      "eval_loss": 1.9373060464859009,
+      "eval_runtime": 185.0999,
+      "eval_samples_per_second": 13.928,
+      "eval_steps_per_second": 6.964,
+      "step": 20
+    },
+    {
+      "epoch": 0.00408313257931485,
+      "grad_norm": 1.8721565008163452,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.9025,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2543150841200640.0,
+  "total_flos": 5040062576197632.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null