Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d8b5451c08782826d55e16fb8ba9d32cce1bf2d9ba8b5db0a7329ee9b15a0a
+oid sha256:6febe872c1ee56a942dced8bf49e59b9d0f7cbe3978af2d53b487e9d769f0a75
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2179112b10ca5276b8390522bb86f7783fdc092155ded556f8d505c68de3d0b6
+oid sha256:26e72c85dbcd1b87585f3b3070ad1f111e821ffe169611c4ad391b480a60b208
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf42ca78ac9a2a869327647eb0aa34446bbb0172e0928c2c921de691f4649efa
+oid sha256:9bf10b5cf8a45272e264b176007f6a12827fa3a39cfbac132e697264744de47a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ca32eaaa7986d6d80e55db6b39c9b365f6d47be6d997e5412cbc79402465c6
+oid sha256:54142b6ca6117f62853f2199ae6d8db9e25b699f5eb4a808448e7a6a68156810
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.023889511011571482,
+  "epoch": 0.03583426651735722,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 115.453,
       "eval_steps_per_second": 57.931,
       "step": 16
+    },
+    {
+      "epoch": 0.0253826054497947,
+      "grad_norm": 0.5249435901641846,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 2.3014,
+      "step": 17
+    },
+    {
+      "epoch": 0.026875699888017916,
+      "grad_norm": 0.39837077260017395,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1987,
+      "step": 18
+    },
+    {
+      "epoch": 0.028368794326241134,
+      "grad_norm": 0.3910773694515228,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 2.2907,
+      "step": 19
+    },
+    {
+      "epoch": 0.029861888764464353,
+      "grad_norm": 0.4713466465473175,
+      "learning_rate": 0.0001,
+      "loss": 2.5941,
+      "step": 20
+    },
+    {
+      "epoch": 0.03135498320268757,
+      "grad_norm": 0.5672959685325623,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.6551,
+      "step": 21
+    },
+    {
+      "epoch": 0.032848077640910786,
+      "grad_norm": 0.36590033769607544,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.4184,
+      "step": 22
+    },
+    {
+      "epoch": 0.03434117207913401,
+      "grad_norm": 0.43650856614112854,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 2.4387,
+      "step": 23
+    },
+    {
+      "epoch": 0.03583426651735722,
+      "grad_norm": 0.45397621393203735,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.1352,
+      "step": 24
+    },
+    {
+      "epoch": 0.03583426651735722,
+      "eval_loss": 2.3984715938568115,
+      "eval_runtime": 2.4672,
+      "eval_samples_per_second": 114.706,
+      "eval_steps_per_second": 57.555,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 89160891236352.0,
+  "total_flos": 132026704330752.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null