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:a0e769fe583b1fe43f7e461439a42bf6117b0bd2756de2dc069dcc31eed67384
+oid sha256:2b7941b2a9cb61ac983217ab3e7d8f2bfe52a778f4486f9fc61ad0a73c6f04ec
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd70d94b81d30c08837e17d910134f5ca109463f7313779e271542a8cd214afc
+oid sha256:388618196a8bc01f7b9c3924edad037a902c6a67fbc668bb89573423be7d0825
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b5e1f0f6702ea1659f883e7fcfe0f4959467a2cf3f972c2046ec9edd45b0aa
+oid sha256:8a787192adbf84242f4b8cb401581e3a7836211ae22a109ec4de70e071b1870b
 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": 0.007112570099849542,
+  "epoch": 0.014225140199699084,
   "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": 14.99,
       "eval_steps_per_second": 7.495,
       "step": 10
+    },
+    {
+      "epoch": 0.008206811653672548,
+      "grad_norm": 8.238612174987793,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.7912,
+      "step": 15
+    },
+    {
+      "epoch": 0.010942415538230063,
+      "grad_norm": 6.331942081451416,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.1827,
+      "step": 20
+    },
+    {
+      "epoch": 0.010942415538230063,
+      "eval_loss": 1.2586541175842285,
+      "eval_runtime": 51.2706,
+      "eval_samples_per_second": 15.018,
+      "eval_steps_per_second": 7.509,
+      "step": 20
+    },
+    {
+      "epoch": 0.01367801942278758,
+      "grad_norm": 3.4683191776275635,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.7444,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2308992761069568.0,
+  "total_flos": 4574419620986880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null