Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64b7c359ca227bb13358640c76c139663e217ce067c05e58e13ebd6ca340968
+oid sha256:eea54761ed1607b29f7e0b424b89c991f493177288ab99163e8f5c7de02a698e
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eeea3f2ee44c47bd8e5d7df938552560a33fda9dfc983aebbfe282fadb54677
+oid sha256:5bcb2d27aefe0220cf79cbc53fece45cbbb4dd13e0ac6ce47cd65e38f138bd4c
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475e61e5257ea8c29bd19f1f5541657fadbaf18eca05eb1b812c0d29deba88c1
+oid sha256:53850beb550ee439f39dd9a26674a0401c26f4be397fed92d41d13b36036343f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0031526403362816357,
+  "epoch": 0.0063052806725632715,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 27.87,
       "eval_steps_per_second": 3.484,
       "step": 9
+    },
+    {
+      "epoch": 0.004203520448375514,
+      "grad_norm": 0.2796209156513214,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.2384,
+      "step": 12
+    },
+    {
+      "epoch": 0.005254400560469393,
+      "grad_norm": 0.28329601883888245,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.2393,
+      "step": 15
+    },
+    {
+      "epoch": 0.0063052806725632715,
+      "grad_norm": 0.22264641523361206,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 1.1474,
+      "step": 18
+    },
+    {
+      "epoch": 0.0063052806725632715,
+      "eval_loss": 1.1840261220932007,
+      "eval_runtime": 172.502,
+      "eval_samples_per_second": 27.872,
+      "eval_steps_per_second": 3.484,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3705727579324416.0,
+  "total_flos": 7411455158648832.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null