Training in progress, epoch 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a618ef5cf269b6c1e073eb60bd9bcb6e6baaf9d63bac08e567e248237330824
+oid sha256:bf7f1711371cdf22625cfd71373d0e13667f9262db729700ebba8bff281e302f
 size 6403448

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a99a17d26069ea1b2300ddb31f582c86c1ffc96ba7d40a5bd87b7b9157de3d5
+oid sha256:fa22af2fc608eb3be5b6d7756926317b864996be333d25aedbb9e48d2d5bd10f
 size 12867066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:010dca2978871dd22e51ccf13e041ea95312e9e51a2d6bc8498d3840cd5050e5
+oid sha256:6a0a24216fd4977ce1d76fe035f83db58fced950e69f3285260aec3babc9a654
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:718198051aa9e8e989e25ac52095d0ce7b7daa6408cffd37d0553cc200763431
+oid sha256:492f28b6539849c91c4a713593f718b0248ba49625b6a14592a3de84ad5d56c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 39,
-  "best_metric": 5.06503438949585,
-  "best_model_checkpoint": "My-Nietzsche-Model/checkpoint-39",
-  "epoch": 3.0,
+  "best_global_step": 52,
+  "best_metric": 5.0411696434021,
+  "best_model_checkpoint": "My-Nietzsche-Model/checkpoint-52",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 39,
+  "global_step": 52,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -32,6 +32,14 @@
       "eval_samples_per_second": 3.24,
       "eval_steps_per_second": 0.81,
       "step": 39
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.0411696434021,
+      "eval_runtime": 6.2271,
+      "eval_samples_per_second": 3.212,
+      "eval_steps_per_second": 0.803,
+      "step": 52
     }
   ],
   "logging_steps": 500,
@@ -51,7 +59,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1870914893875200.0,
+  "total_flos": 2494553191833600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null