Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c900884e78a32f3a7e9eee1e87b43e4de5c8578537a58cc53459f787f32e6ec
+oid sha256:ca504fb7c673009e3dedec6288d8cb1613bed2aaa7cbf0e33b9e91cf3f45b183
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0183cfb2b8d2eac99ff8a929a20f08cd2fa1836cd3a04ec8ad124ab493fd2586
+oid sha256:0a2e49c903c5529c79d3ff835b7da0b2d73bd7966896684017c45f52ef8574c9
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5e3c19f7b2892f9204c2db9ed620b572aab049411a4232f39c90287c803cca
+oid sha256:5aef72e80bca5ad86c4740cd44eaa6a311a9485d9a446667badbb08fac831b01
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35459df988092e3ff9e3c1b91118d006576bed7e1956fe6101d7671fcd8c5396
+oid sha256:472d41c9b9333a74c9178e69008f711ff75ebcb1c9882a89e4e8e8fceffd9b44
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18832050701674966,
+  "epoch": 0.3766410140334993,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 11.246,
       "eval_steps_per_second": 2.83,
       "step": 13
+    },
+    {
+      "epoch": 0.20280669986419195,
+      "grad_norm": 227.82803344726562,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 45.4463,
+      "step": 14
+    },
+    {
+      "epoch": 0.2172928927116342,
+      "grad_norm": 233.84213256835938,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 40.7913,
+      "step": 15
+    },
+    {
+      "epoch": 0.2317790855590765,
+      "grad_norm": 241.74923706054688,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 36.8332,
+      "step": 16
+    },
+    {
+      "epoch": 0.2462652784065188,
+      "grad_norm": 273.61724853515625,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 33.5054,
+      "step": 17
+    },
+    {
+      "epoch": 0.2607514712539611,
+      "grad_norm": 336.7424011230469,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 26.3073,
+      "step": 18
+    },
+    {
+      "epoch": 0.2752376641014033,
+      "grad_norm": 398.2518005371094,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 29.1703,
+      "step": 19
+    },
+    {
+      "epoch": 0.2897238569488456,
+      "grad_norm": 263.69000244140625,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 25.753,
+      "step": 20
+    },
+    {
+      "epoch": 0.3042100497962879,
+      "grad_norm": 140.5085906982422,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 24.2245,
+      "step": 21
+    },
+    {
+      "epoch": 0.3186962426437302,
+      "grad_norm": 126.79087829589844,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 20.9214,
+      "step": 22
+    },
+    {
+      "epoch": 0.3331824354911725,
+      "grad_norm": 126.19627380371094,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 19.3473,
+      "step": 23
+    },
+    {
+      "epoch": 0.3476686283386148,
+      "grad_norm": 218.7227325439453,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 23.4087,
+      "step": 24
+    },
+    {
+      "epoch": 0.362154821186057,
+      "grad_norm": 117.1246566772461,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 18.8893,
+      "step": 25
+    },
+    {
+      "epoch": 0.3766410140334993,
+      "grad_norm": 319.6368103027344,
+      "learning_rate": 5e-05,
+      "loss": 21.5772,
+      "step": 26
+    },
+    {
+      "epoch": 0.3766410140334993,
+      "eval_loss": 0.5946769714355469,
+      "eval_runtime": 41.3369,
+      "eval_samples_per_second": 11.249,
+      "eval_steps_per_second": 2.83,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.925072315706245e+17,
+  "total_flos": 5.85014463141249e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null