Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad60697384b411d4e6824ea48ac1e9272d7ea5fe0e18c8f17a05028ded8dd5e0
+oid sha256:f69b8d3ddca774ae27304168f3b28da37712b7da2aca30e638aec7f032b92993
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e54e92dde0c8059084fe3634d2a9d35307d4b8d58926ef37a9f4c7b9240a159f
+oid sha256:af5ae3146580843acf35822f7a5104177ee493fd4724c883e8e682d8ababceb2
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0a880b94d9b8f1377e86006043b94121eb1c447497937e3f4ae33277dae97f
+oid sha256:9f16f3b8874379bf8e1e039ef0bfa9f44be83be43b977ccd15b78395a275f501
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004691256670380578,
+  "epoch": 0.0009382513340761156,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 4.27,
       "eval_steps_per_second": 2.135,
       "step": 2
+    },
+    {
+      "epoch": 0.0007036885005570867,
+      "grad_norm": 8.586624145507812,
+      "learning_rate": 3e-05,
+      "loss": 35.9909,
+      "step": 3
+    },
+    {
+      "epoch": 0.0009382513340761156,
+      "grad_norm": 11.132521629333496,
+      "learning_rate": 4e-05,
+      "loss": 47.7162,
+      "step": 4
+    },
+    {
+      "epoch": 0.0009382513340761156,
+      "eval_loss": NaN,
+      "eval_runtime": 394.1002,
+      "eval_samples_per_second": 18.221,
+      "eval_steps_per_second": 9.112,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2532963338158080.0,
+  "total_flos": 5065926676316160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null