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:bb290fc1ad5ec42962fc11c1d25272019c032f1f8702388e8191adfca662a8aa
+oid sha256:da9ea6b73a907aa31aff8be6c083558c978427492601fdaa43d754bdfc1240ab
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d367a5380a328fecbd80875c580d669cd4df64c4065c6f3df02b5d101ecec26c
+oid sha256:a5c32586eaa167e240f59e86602ecff0c974259bc26c29b8d753b93409b4b755
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2128e47ed2e40d2cfe486fec9abc63fcf3bab8260c2a57f50edbff5866f86c2f
+oid sha256:3f72abeeabde10b9d84b3462603134abfc2c7ba312eade559889669ab6701efc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0868657339736897,
+  "epoch": 0.13029860096053456,
   "eval_steps": 10,
-  "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": 32.914,
       "eval_steps_per_second": 4.128,
       "step": 20
+    },
+    {
+      "epoch": 0.10022969304656504,
+      "grad_norm": 0.661380410194397,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.374,
+      "step": 30
+    },
+    {
+      "epoch": 0.10022969304656504,
+      "eval_loss": NaN,
+      "eval_runtime": 61.2117,
+      "eval_samples_per_second": 32.951,
+      "eval_steps_per_second": 4.133,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.894207870042112e+16,
+  "total_flos": 4.341311805063168e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null