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:c9a50b25f95230242a5e9cc1095bdab422d63485b149fdebacba92ea0502589a
+oid sha256:3cb421132bc89a9c76e0db8bd08ac3b7183d01154ca6a751c2ae74ef88bdfe83
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:facef6acb35856cd479fca9631711ca4959db9a0918b6c71dc09c86eaa2bea35
+oid sha256:75bf40a6433f9b526167356c5bb1a12f0e5773676cdd39f94010c260da77fc2a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d16ff0bfacfd2f18079148975e84c618416840e27c58d67c3def77f9fe9a111
+oid sha256:4a8cb3fa95b19277c546f2944ac11cb384ba5fe8f2ef886c6f07e6edb2d31ba0
 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": 0.006968641114982578,
+  "epoch": 0.013937282229965157,
   "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": 11.572,
       "eval_steps_per_second": 1.447,
       "step": 9
+    },
+    {
+      "epoch": 0.009291521486643438,
+      "grad_norm": 5.306800842285156,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.2852,
+      "step": 12
+    },
+    {
+      "epoch": 0.011614401858304297,
+      "grad_norm": 3.0954625606536865,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.1949,
+      "step": 15
+    },
+    {
+      "epoch": 0.013937282229965157,
+      "grad_norm": 1.6799471378326416,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0677,
+      "step": 18
+    },
+    {
+      "epoch": 0.013937282229965157,
+      "eval_loss": 0.010273167863488197,
+      "eval_runtime": 188.1518,
+      "eval_samples_per_second": 11.565,
+      "eval_steps_per_second": 1.446,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6530810303676416e+16,
+  "total_flos": 3.376505934367949e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null