Training in progress, step 28, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dccf55329b9f1713b01fc9b376817612e23552203b71f6f407f548e83094705d
+oid sha256:5e124b45ee1df21c68eb148c7df8bacc371efa2fb6216855fea877456cc02de6
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f382e330c1d2a70b2710fc48891893685bac8d4111d3348ef97aedc70487188
+oid sha256:4f6b195f28f94e374b282cb0ab6fe261d0d3711cbb0575f65a3ace5145ccedce
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72209a0ef07e646c4de33cbbfe4b4d8a262be6d499edc700653a7c04dc79dab
+oid sha256:b13ce8308266d915bd25b0b391764f5c10e112e199f7f6edacd41d5676538b0a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c7e21bc965f34fd3d72d9cb2881ca0e9f4bcb64151c1f8562417f8d5125510
+oid sha256:7ed58e5b5053e09a44cd1fe67ab0f07cc790b003abec6db1f957ea4f926e4423
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01062618595825427,
+  "epoch": 0.02125237191650854,
   "eval_steps": 14,
-  "global_step": 14,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 49.542,
       "eval_steps_per_second": 24.771,
       "step": 14
+    },
+    {
+      "epoch": 0.015180265654648957,
+      "grad_norm": 4.966372489929199,
+      "learning_rate": 0.0002,
+      "loss": 1.2173,
+      "step": 20
+    },
+    {
+      "epoch": 0.02125237191650854,
+      "eval_loss": 1.1263376474380493,
+      "eval_runtime": 5.716,
+      "eval_samples_per_second": 48.635,
+      "eval_steps_per_second": 24.318,
+      "step": 28
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 231773577412608.0,
+  "total_flos": 463547154825216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null