Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d789104383c01da329d85d26ab9996b281d91fd0d8439c03ac2673c0b1795af
+oid sha256:10f8888d7e6f03a4c0ebda69aa0ab7aeaac366b5345fbbd7a26b41190d371aee
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2862840ee22c8badea609ebc5ed842f9ccfe9e2a4690852580bf44b0dffa449d
+oid sha256:92dc7630d04eeb00346e2dcd30a8e5b4cfeca565bfae56c8a54b021fd8058509
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad547b62804e21a6e8157e048359d3d64ae9283c7a7077358e31c0dc7ae3d112
+oid sha256:fddf0ba50d83fdbdc2b6d9ec9f3e1f8f7bfba7e0848c5b0caf52590efbfd919c
 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": 0.0048867587632741285,
+  "epoch": 0.009773517526548257,
   "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": 30.85,
       "eval_steps_per_second": 15.439,
       "step": 10
+    },
+    {
+      "epoch": 0.00563856780377784,
+      "grad_norm": 0.23296763002872467,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.1673,
+      "step": 15
+    },
+    {
+      "epoch": 0.007518090405037121,
+      "grad_norm": 1.240827202796936,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.2802,
+      "step": 20
+    },
+    {
+      "epoch": 0.007518090405037121,
+      "eval_loss": 0.15440116822719574,
+      "eval_runtime": 36.498,
+      "eval_samples_per_second": 30.714,
+      "eval_steps_per_second": 15.371,
+      "step": 20
+    },
+    {
+      "epoch": 0.0093976130062964,
+      "grad_norm": 0.27838045358657837,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1353,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 639479945625600.0,
+  "total_flos": 1278959891251200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null