Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec33ca2fc0d8718806e5f420bf04066437038e37d5b653b6a9b2c43001701d0
+oid sha256:2bca28280c0dbe56522370f6d88042e0d2fbb0e1c9ed4761183fa32e6529bf40
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad22a4bcef660e8243a0bd540b75a04cfd689a0c573b2d02cc8091a9dba73c0
+oid sha256:02e53a0d95313efbaf7a1f1b67aeb38ced860a01d2411e5b6748254a17868ed9
 size 61392180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd0a7014311c2c3ae059a8e9bd0bb262b013708051cda2cf684f23b213466ba
+oid sha256:1b77339b9636663a15a3d518f387e0d75c80cf9510a36c6431f57765d1c338de
 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": 0.006074924063449207,
+  "epoch": 0.012149848126898413,
   "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": 22.544,
       "eval_steps_per_second": 2.819,
       "step": 9
+    },
+    {
+      "epoch": 0.00809989875126561,
+      "grad_norm": 1.4622615575790405,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.6239,
+      "step": 12
+    },
+    {
+      "epoch": 0.010124873439082012,
+      "grad_norm": 1.6571316719055176,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.3919,
+      "step": 15
+    },
+    {
+      "epoch": 0.012149848126898413,
+      "grad_norm": 0.7293809056282043,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 1.1924,
+      "step": 18
+    },
+    {
+      "epoch": 0.012149848126898413,
+      "eval_loss": 1.1869244575500488,
+      "eval_runtime": 110.6832,
+      "eval_samples_per_second": 22.542,
+      "eval_steps_per_second": 2.819,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4962851085090816.0,
+  "total_flos": 9925702170181632.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null