Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a2260ff562c50cc6783715f0ca88706894c0de7fc0589b24ad930a34fc977c6
+oid sha256:c71a73928d95fc41ae37e66110fe29b61a6f527f4fa532723a721b6615a900a6
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:798d02660bdc1674ad293b23d6181f512cb74fd0c934096aed2afcf58754c860
+oid sha256:c6261cea29460c5c670658e1e85215fcdd0674d2248598dd29bc394ddd2620a5
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec5e393df389bb457c35a33330f25a8f6a180b16c6cb0bfd32a205408f04baca
+oid sha256:301ec27088a2135475d0bae8b6d448064f7cd7e1e09162d34572ebe2cc31429b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef0e768220ab06b0b8ca60bf0cb82c3ba1ffa61503120e1cf6e3622be29cf83
+oid sha256:053f8a597fb71bde446a175404cc18fe6996cf501293c3abfb94953dfd03d780
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06474237928243863,
+  "epoch": 0.08632317237658484,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 4.984,
       "eval_steps_per_second": 2.495,
       "step": 30
+    },
+    {
+      "epoch": 0.08632317237658484,
+      "grad_norm": 4.422735691070557,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 1.9042,
+      "step": 40
+    },
+    {
+      "epoch": 0.08632317237658484,
+      "eval_loss": 0.09215810149908066,
+      "eval_runtime": 158.3154,
+      "eval_samples_per_second": 4.933,
+      "eval_steps_per_second": 2.47,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.94719401984e+16,
+  "total_flos": 6.5302961061888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null