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:bb8b2933c15d6f1696b1d02c8926cbfeb9dab59ade311f73a60461cd150de056
+oid sha256:f0973623cc8dc43bc5e669047561c39d8f0afbf1b60f121d20121ae4429d673a
 size 247936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3dbda4de538fac2fcabb9e4474d2fdb6e0c50fe23ce1f3b77e1844ffada2c0
+oid sha256:f8b62de692ba4f4e3af2c1323ed977e0efc4274204bf835012cba70f20786f2b
 size 263024

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0672016e5d3daef59beed617e06e8a6fe522990497a345549b30ecc186be592
+oid sha256:5d38d3e87897391be07ecebae20ad9e6a748f69c706e993d8ddaf8a08f395a21
 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": 0.010230179028132993,
+  "epoch": 0.020460358056265986,
   "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": 154.915,
       "eval_steps_per_second": 38.885,
       "step": 9
+    },
+    {
+      "epoch": 0.013640238704177323,
+      "grad_norm": 2.743508815765381,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 44.2612,
+      "step": 12
+    },
+    {
+      "epoch": 0.017050298380221655,
+      "grad_norm": 1.8524738550186157,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 44.2154,
+      "step": 15
+    },
+    {
+      "epoch": 0.020460358056265986,
+      "grad_norm": 1.639198660850525,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 44.167,
+      "step": 18
+    },
+    {
+      "epoch": 0.020460358056265986,
+      "eval_loss": 11.030960083007812,
+      "eval_runtime": 4.7631,
+      "eval_samples_per_second": 155.569,
+      "eval_steps_per_second": 39.05,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 88937594880.0,
+  "total_flos": 165465292800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null