Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba2f487423f3ee403b2b9cdb4410a466f0cfdb517e419c5c9a80cb48c89a3db
+oid sha256:8a618ef5cf269b6c1e073eb60bd9bcb6e6baaf9d63bac08e567e248237330824
 size 6403448

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15eae082e01864f410ba2f95b77b0ebd570f80467f63f7660dd0f19a4ab71015
+oid sha256:6a99a17d26069ea1b2300ddb31f582c86c1ffc96ba7d40a5bd87b7b9157de3d5
 size 12867066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf172885e90853de4ff46d2054e9b24daa1c6a6ad504c5b28bcf6f9d1bef903
+oid sha256:010dca2978871dd22e51ccf13e041ea95312e9e51a2d6bc8498d3840cd5050e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fd4b24a386a8e80db11b364387d0eebec81beeabc63133ccb6bc22dfcfddf0
+oid sha256:718198051aa9e8e989e25ac52095d0ce7b7daa6408cffd37d0553cc200763431
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 26,
-  "best_metric": 5.1018967628479,
-  "best_model_checkpoint": "My-Nietzsche-Model/checkpoint-26",
-  "epoch": 2.0,
+  "best_global_step": 39,
+  "best_metric": 5.06503438949585,
+  "best_model_checkpoint": "My-Nietzsche-Model/checkpoint-39",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -24,6 +24,14 @@
       "eval_samples_per_second": 3.211,
       "eval_steps_per_second": 0.803,
       "step": 26
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.06503438949585,
+      "eval_runtime": 6.173,
+      "eval_samples_per_second": 3.24,
+      "eval_steps_per_second": 0.81,
+      "step": 39
     }
   ],
   "logging_steps": 500,
@@ -43,7 +51,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1247276595916800.0,
+  "total_flos": 1870914893875200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null