Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9a2020e1e81d0db67dfcd552427f0a1a14ec3f0d786a74ed0dad73ca0464dfe
+oid sha256:e5992c4e5d848cc8cfff3cc1694bafe0e48debf526e69aabb6b4eaed8dc439b3
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397e8a23b7552f60370d1700a97b449a0325dda9181fdf7c74ea250d27578e23
+oid sha256:524841ef651f1ff5beda9115deaf7b957e23f74b41cdae3a3acef8460cf7d900
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30bafe9aa09d6f08852f65e3dd3a748ba867975cde5b463006fc3b71b5ae9261
+oid sha256:d1acdb0eca205662ef346af00c08ae1c6937e126fabf6eb997cb39d88eb2c740
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:1b92f6a8c8f69a383a7378c8526c34c47aacb6959ba4f705f8fb8753791be375
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4,
+  "epoch": 2.7,
   "eval_steps": 3,
-  "global_step": 24,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -135,6 +135,21 @@
       "eval_samples_per_second": 13.988,
       "eval_steps_per_second": 2.468,
       "step": 24
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.8103647232055664,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.5713,
+      "step": 27
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 1.127324104309082,
+      "eval_runtime": 1.2229,
+      "eval_samples_per_second": 13.902,
+      "eval_steps_per_second": 2.453,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -154,7 +169,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.368098823405568e+16,
+  "total_flos": 3.794665429008384e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null