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:f065171b9c2a941c6db6887c2df56e9eee64324358f8691b407e62fcc4d6ce48
+oid sha256:702866f662a9b54554c1219259dfe7b88d958b15e67048b8a4848cbc01da3997
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5cbdd9136cc98a2e40352614a0df30f74b821b277012e2e8f39f31fb4da3b4
+oid sha256:2e4e8e3e57d09fb85cb69b77c9385b9429058ddaf4ca8520fbcfeefa72f01380
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
+oid sha256:4a997aa8bfab00a35d7cfa486126e3d295d226a899068a295415cfc8e8058a7c
 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": 0.002638522427440633,
+  "epoch": 0.005277044854881266,
   "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": 33.722,
       "eval_steps_per_second": 16.869,
       "step": 10
+    },
+    {
+      "epoch": 0.003044448954739192,
+      "grad_norm": 1.8466225862503052,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.5546,
+      "step": 15
+    },
+    {
+      "epoch": 0.004059265272985589,
+      "grad_norm": 2.247924327850342,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.1787,
+      "step": 20
+    },
+    {
+      "epoch": 0.004059265272985589,
+      "eval_loss": 1.8443979024887085,
+      "eval_runtime": 61.9335,
+      "eval_samples_per_second": 33.504,
+      "eval_steps_per_second": 16.76,
+      "step": 20
+    },
+    {
+      "epoch": 0.005074081591231987,
+      "grad_norm": 2.343292713165283,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.599,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 332529571725312.0,
+  "total_flos": 665059143450624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null