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:d6359bda9377ef925d149fdbd33133204acfe252ba7f326ba906bf46b20a3456
+oid sha256:82094566cd6a6e57fffce2dc3c6177d0588e34db372f75b446150c72832000fa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d0ea69819271471ab435b2e3ff04a978d0163a06811500d1d02b2c1fb72edd
+oid sha256:1f27ed0b9ea5e4f2b77599cb03647b066318942b52cace7cd6e6d26e97d6066e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 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": 0.023138105567606652,
+  "epoch": 0.046276211135213303,
   "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": 41.28,
       "eval_steps_per_second": 20.64,
       "step": 2
+    },
+    {
+      "epoch": 0.03470715835140998,
+      "grad_norm": 5.456160068511963,
+      "learning_rate": 3e-05,
+      "loss": 20.8095,
+      "step": 3
+    },
+    {
+      "epoch": 0.046276211135213303,
+      "grad_norm": 5.923030376434326,
+      "learning_rate": 4e-05,
+      "loss": 20.7911,
+      "step": 4
+    },
+    {
+      "epoch": 0.046276211135213303,
+      "eval_loss": NaN,
+      "eval_runtime": 3.5704,
+      "eval_samples_per_second": 40.892,
+      "eval_steps_per_second": 20.446,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1479651398516736.0,
+  "total_flos": 2959302797033472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null