Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a4485b6a5f308d882200e24c2922b587302c04718ab2dc39b762c0a4c37df5
+oid sha256:46cb47f40e4a7796c364f05315ae08acb811947ed345886eda48acc0ec2d2245
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5f46766dc06153b0faf7f4484cf684f892bd77c4c8c6bc28c5daeaf71eafb4
+oid sha256:2c22333630c548e3d961650c7137c3596f60226d48f4845e05fbf9184062f4e7
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59a0f2b0270d4b176708c17836484f6e61cd61151d7e53ecc05f63694ff46ce
+oid sha256:bc00b9f52758d38c42c2ddebf352af881abc12afc428f73da93ca1f1a54273a1
 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": 0.0221606648199446,
+  "epoch": 0.0443213296398892,
   "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": 5.84,
       "eval_steps_per_second": 2.939,
       "step": 2
+    },
+    {
+      "epoch": 0.0332409972299169,
+      "grad_norm": 3.4211461544036865,
+      "learning_rate": 3e-05,
+      "loss": 14.7803,
+      "step": 3
+    },
+    {
+      "epoch": 0.0443213296398892,
+      "grad_norm": 4.920835018157959,
+      "learning_rate": 4e-05,
+      "loss": 14.4866,
+      "step": 4
+    },
+    {
+      "epoch": 0.0443213296398892,
+      "eval_loss": NaN,
+      "eval_runtime": 26.1581,
+      "eval_samples_per_second": 5.849,
+      "eval_steps_per_second": 2.944,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1628733135912960.0,
+  "total_flos": 3298184600223744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null