Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346d725b59d57b9cf4b75a54870c7ac0296aeb5500ca9ce72d6b335f43c6aff2
+oid sha256:33440e9d041e98372f9c3745546a5a7cc6986bb0e05661553ad9752d3aef4911
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9658a2e962c2a4df6dc47aff10e87ea29d673c14cf6462f9a19616f53d8332a
+oid sha256:c6133efffc392369d67150ecc3099ef89b5461db66932860bf5b55d38dde2a99
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9728c6e0d6d918e6f165e031e67f5dccd545dd26a31f3497fd544c025166c7b5
+oid sha256:fb488ddaac30717057cafba2b63eb6beb2bfa4396579dbd215ca2d77215fe7a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c50acebbdd320cdbda27b93feb5d91578ce2eb03d7fc0517b7bfffd55baef8
+oid sha256:10e175ebe60f1a6bbd43d635188097fdd53bf710ff976db3f946328fc19cf4ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0022550297734399774,
+  "epoch": 0.0025369084951199746,
   "eval_steps": 2,
-  "global_step": 16,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,28 @@
       "eval_samples_per_second": 244.333,
       "eval_steps_per_second": 122.166,
       "step": 16
+    },
+    {
+      "epoch": 0.002395969134279976,
+      "grad_norm": 0.5067576766014099,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3954,
+      "step": 17
+    },
+    {
+      "epoch": 0.0025369084951199746,
+      "grad_norm": 0.40567123889923096,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3808,
+      "step": 18
+    },
+    {
+      "epoch": 0.0025369084951199746,
+      "eval_loss": NaN,
+      "eval_runtime": 12.1062,
+      "eval_samples_per_second": 246.815,
+      "eval_steps_per_second": 123.408,
+      "step": 18
     }
   ],
   "logging_steps": 1,
@@ -210,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 418419572736.0,
+  "total_flos": 470722019328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null