Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0beb808774e1923321b7fb141b4494865b3d94e6f1b542d7d2cb52a54ba285
+oid sha256:6341075ce9f542c41e6fdf0790e59918346224d90350bc2fcc18fbca5b61854d
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270005343d0c084d7cc999855274ebdf404c73b3261fa135a2a48afa6c2f77be
+oid sha256:b516a2c87cc42f087e77203aad4b4a4c563d5c49c8345f909ab0b751a5c2f415
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ece35dc50cc5ee4af4ab69a28477eb5dd636d6536a20bde0562d44499f2a357
+oid sha256:0c5e843a3007417b54718c9360bff0f4c72b8e2a4e589e479eb4a6b3b7a981de
 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": 0.002198266751215388,
+  "epoch": 0.004396533502430776,
   "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": 17.36,
       "eval_steps_per_second": 8.68,
       "step": 10
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 0.2895045876502991,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.5513,
+      "step": 15
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "grad_norm": 0.40199053287506104,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.5115,
+      "step": 20
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "eval_loss": 0.5287407636642456,
+      "eval_runtime": 143.8791,
+      "eval_samples_per_second": 17.306,
+      "eval_steps_per_second": 8.653,
+      "step": 20
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "grad_norm": 0.4052754342556,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.4523,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1461018395934720.0,
+  "total_flos": 2956822944153600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null