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:b5751c8354669c7f8697c3dc43caf304299201e2b3ab9bcf172f814321e44a8a
+oid sha256:4be2626d3b87d9dbd789da90488adc34acc26530f34be6279b08c5cdd50310cc
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c006f948b1468f9e0a2970c26e4cacd91774b0f0bca69c93222acc87f71bbe1a
+oid sha256:985c1381512b3380f5f38cfff918a152258ae3bb132b9e3d40910503fd9c7f83
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3c21661c0b01be713737b8dd62ec2e722319e094b58bf7a422b2c1a5cb4804e
+oid sha256:f365462a622095c1188d25620d5e08eaced77b1a289f50e3e26cffab7c3f7d8b
 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": 6.815122757398668e-05,
+  "epoch": 0.00013630245514797336,
   "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": 107.921,
       "eval_steps_per_second": 53.965,
       "step": 2
+    },
+    {
+      "epoch": 0.00010222684136098001,
+      "grad_norm": 2.257598876953125,
+      "learning_rate": 3e-05,
+      "loss": 44.3175,
+      "step": 3
+    },
+    {
+      "epoch": 0.00013630245514797336,
+      "grad_norm": 3.2154581546783447,
+      "learning_rate": 4e-05,
+      "loss": 44.4066,
+      "step": 4
+    },
+    {
+      "epoch": 0.00013630245514797336,
+      "eval_loss": 11.092741012573242,
+      "eval_runtime": 114.161,
+      "eval_samples_per_second": 108.242,
+      "eval_steps_per_second": 54.125,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6083051520.0,
+  "total_flos": 12166103040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null