Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f152a79dfc263e26e6a9c3c96fe9a23f63d146ce7c47503ec13da69c0027b72
+oid sha256:bc5b8361298d83905b59c33a458c409c54e2135768fb1253891af9fe1bfd2820
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6521eb254c737846d47f30ccbb5da807c646d045eb119759339549930a5ade1c
+oid sha256:212299ba4b0ae828447f1bf2a45f8aab97752933885c113e4426bcbcc2937e9d
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af34c3366fea9ce850ca0b6277cacb085fd4be2ce7e4448befe12b5abfd60d8
+oid sha256:b3622d63468ec09dd09d8d03c204beeea583ff91c4753b52b69ac9b5ccb43178
 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": 0.0011265622249603943,
+  "epoch": 0.0022531244499207886,
   "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": 4.786,
       "eval_steps_per_second": 2.393,
       "step": 2
+    },
+    {
+      "epoch": 0.0016898433374405914,
+      "grad_norm": 11.927529335021973,
+      "learning_rate": 3e-05,
+      "loss": 62.9045,
+      "step": 3
+    },
+    {
+      "epoch": 0.0022531244499207886,
+      "grad_norm": 13.698987007141113,
+      "learning_rate": 4e-05,
+      "loss": 62.3275,
+      "step": 4
+    },
+    {
+      "epoch": 0.0022531244499207886,
+      "eval_loss": 3.778285026550293,
+      "eval_runtime": 644.7439,
+      "eval_samples_per_second": 4.638,
+      "eval_steps_per_second": 2.319,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2402405132009472.0,
+  "total_flos": 4764091532967936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null