Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc1e5400806244192b4bf5e686d72eafd68fbbadd034f980ace3542b0904865
+oid sha256:27e5dbb07812387426960b54de6311886f59720fbbb295dc442fe375b3d1a63d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c7b10b894d922e36f6068a02e4acf9cde47e3c233b2af55c4af65d0f55a04a
+oid sha256:c59727fbfa2d6fb9acfbb6a4d58b05e1a053e4a17cc881af5f47cbae69b72c5f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b274d200228065c5ad050511a1f7866a6edb57bdaa953138cf781ba60f5569eb
+oid sha256:d73744cc9da6cf4515a44034b122856d46a3fed397efa1e527493ee573696292
 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": 0.004626283070695388,
+  "epoch": 0.009252566141390776,
   "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": 22.348,
       "eval_steps_per_second": 11.19,
       "step": 2
+    },
+    {
+      "epoch": 0.0069394246060430825,
+      "grad_norm": 192.53724670410156,
+      "learning_rate": 3e-05,
+      "loss": 113.4672,
+      "step": 3
+    },
+    {
+      "epoch": 0.009252566141390776,
+      "grad_norm": 172.92764282226562,
+      "learning_rate": 4e-05,
+      "loss": 113.4296,
+      "step": 4
+    },
+    {
+      "epoch": 0.009252566141390776,
+      "eval_loss": NaN,
+      "eval_runtime": 33.623,
+      "eval_samples_per_second": 21.682,
+      "eval_steps_per_second": 10.856,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1402135828758528.0,
+  "total_flos": 2804271657517056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null