Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6374d3e4dfc6c44a6b12fff66e8eb562b7d405250b023d028d70702c20de3f
+oid sha256:4f73159bdfa49c703b17f320763b6f928b7206072e3253282424cf94330ddad3
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f48923b1d3d438f6e1a2450f29e16a629e77f04bd0d7da099481bc6d6463a3f
+oid sha256:e46501678e510c7ab814cdc829620eceeaac5b627924c800dc3142125ab24bc5
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bbba064701c6c5641a803b1cc6ad3663ec5a37b46a361f1a3f2ad360548d26
+oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
 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": 0.0045127626568890146,
+  "epoch": 0.009025525313778029,
   "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": 801.543,
       "eval_steps_per_second": 401.308,
       "step": 2
+    },
+    {
+      "epoch": 0.006769143985333521,
+      "grad_norm": 0.03374136611819267,
+      "learning_rate": 3e-05,
+      "loss": 10.3716,
+      "step": 3
+    },
+    {
+      "epoch": 0.009025525313778029,
+      "grad_norm": 0.033730849623680115,
+      "learning_rate": 4e-05,
+      "loss": 10.3705,
+      "step": 4
+    },
+    {
+      "epoch": 0.009025525313778029,
+      "eval_loss": 10.371350288391113,
+      "eval_runtime": 0.9394,
+      "eval_samples_per_second": 795.222,
+      "eval_steps_per_second": 398.143,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 103447265280.0,
+  "total_flos": 206894530560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null