Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d8a03386325b6d2a116ced8280291b6582d7faabec941d071c433b70861cc5
+oid sha256:d4978abff3959d181a60616b9fe70b0dff6e5469e4dbc60268d5ed49e3188c42
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48b8079a83399b4aee27284a7cba82b76dcb04fa3f398a9cbeebf761df1ceb4
+oid sha256:115d5500f52a1e3ea7ca701230719782e67dbb85bbdd9882f903e243795ec7f7
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b630e1544514159eadb2231e3dcb5f9a87dc415b5488d4bb569ee5560d1d32ae
+oid sha256:cbf433e815bcfb3615ba2122a948b4904fc7b63110f4cc06d5f59bbf9003d456
 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": 0.0010584810796507012,
+  "epoch": 0.0021169621593014024,
   "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": 15.641,
       "eval_steps_per_second": 7.82,
       "step": 10
+    },
+    {
+      "epoch": 0.001221324322673886,
+      "grad_norm": 2.1531338691711426,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.3268,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016284324302318482,
+      "grad_norm": 2.4186878204345703,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.9394,
+      "step": 20
+    },
+    {
+      "epoch": 0.0016284324302318482,
+      "eval_loss": 1.9988257884979248,
+      "eval_runtime": 330.9251,
+      "eval_samples_per_second": 15.629,
+      "eval_steps_per_second": 7.814,
+      "step": 20
+    },
+    {
+      "epoch": 0.0020355405377898103,
+      "grad_norm": 2.270822763442993,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.9121,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2009119229214720.0,
+  "total_flos": 4038739675054080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null