Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57e6a53b0a6f445bbfe58bfb8eb4a0facf1a178ded76205a05772d31d1921d6
+oid sha256:d5ca847cad4011cb1ca4916d8094691331875044484feee92a7eaedbcb25b406
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388a1d2158bf61f400eb1cd61b31752153e6ab5e31eeee0feb7dfb1297f3c0ea
+oid sha256:833e79eeba36bdf93b1dbd6bfc041c9150fcfbbe9202f81f010bd5efddef630c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9abf883c2e9c09674e212674962f98f5fa416abc3e528367d43967e85b78711
+oid sha256:f6772af577974c8afd4f01c292dee37aefb71155f4658c2cd442b9995c16c293
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010798463295607933,
+  "epoch": 0.0161976949434119,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 17.673,
       "eval_steps_per_second": 8.837,
       "step": 26
+    },
+    {
+      "epoch": 0.012459765341086075,
+      "grad_norm": 0.3119395077228546,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.6132,
+      "step": 30
+    },
+    {
+      "epoch": 0.0161976949434119,
+      "eval_loss": 0.5670517086982727,
+      "eval_runtime": 57.3936,
+      "eval_samples_per_second": 17.667,
+      "eval_steps_per_second": 8.834,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8568679201505280.0,
+  "total_flos": 1.285301880225792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null