Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eec26cd0c921fc9e9c8f092b29801c7bd2c054c7b6e26a690bbf06da8f21987
+oid sha256:81f0cf86ce50f6786f1c55af0478d03ed3319bbebf2af398ff054c8961848143
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:245ae9cc3955b089056be740e8d79b18f6d9bc333e017703bf22ea8aed542f62
+oid sha256:c58b388eb7d6d2a0ef75d85c6cd3209e51a70890b32551245908d88361c2a77f
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d41e780f6f8db2d84292a4579c83fc105cfc0f4ebc331ae11cd9a51338da323
+oid sha256:2dfde186a246679aff5ac812ee1b48959224a51864d34e011b4ef4c38ee651cc
 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": 0.0004034980174280105,
+  "epoch": 0.000806996034856021,
   "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": 10.004,
       "eval_steps_per_second": 5.002,
       "step": 10
+    },
+    {
+      "epoch": 0.0004655746354938583,
+      "grad_norm": 2.4750373363494873,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.5722,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006207661806584777,
+      "grad_norm": 1.5241283178329468,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.5678,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006207661806584777,
+      "eval_loss": 1.1251658201217651,
+      "eval_runtime": 1355.943,
+      "eval_samples_per_second": 10.005,
+      "eval_steps_per_second": 5.002,
+      "step": 20
+    },
+    {
+      "epoch": 0.0007759577258230971,
+      "grad_norm": 1.527565360069275,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.1063,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4071873105100800.0,
+  "total_flos": 7940152554946560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null