Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529254a4d9786a97e90da4397d1ac996dd0c8abc764cf9fedbbb700c22015040
+oid sha256:1bebc6f61c7de98206559d6c0c94746fec850053ae01604695dbc28ec389394f
 size 1134088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd75f4bc5dc6fb896acf6dad9db6b72eb321fa1533b91db159d9dbb55dec8d44
+oid sha256:4af5ccff3dc5e99701589efd0f6250525d8f198952310ba225cc00a5120b5b21
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b7b3c5e0224a100d07790dce638f6ef26ebe7a218168fc915f411741c3a42f
+oid sha256:8722eae63c381f92c6d94d24ace69d7fcf532d72874bbfed0a1d65ec7ba4cff9
 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": 0.37309417040358744,
+  "epoch": 0.5596412556053811,
   "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": 317.639,
       "eval_steps_per_second": 39.874,
       "step": 20
+    },
+    {
+      "epoch": 0.4304932735426009,
+      "grad_norm": 1.3032526969909668,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.7502,
+      "step": 30
+    },
+    {
+      "epoch": 0.4304932735426009,
+      "eval_loss": 1.653484582901001,
+      "eval_runtime": 1.4493,
+      "eval_samples_per_second": 324.296,
+      "eval_steps_per_second": 40.71,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 864200612118528.0,
+  "total_flos": 1294151165411328.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null