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:e68e8beac1289b386c60c029ddf99928f61bfc3103f092fa0cf13c8f28b1dc46
+oid sha256:37d7307b1ab7606d396b2c07bcd797d79f2dcb319a486f398f7e6d5c8384655a
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fed090afec57b575889868c8c6d260c4f648167574288f177038568472d7c98f
+oid sha256:70047662bd8d70318fb7c750c85dea89d6049b1ca9bf4e43a6e6fd5b4df971d1
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4a3ee778160f42a22e93367025f5b4d76e7fc51b428625824d02549c0d97d5
+oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005264756505011643,
+  "epoch": 0.010529513010023287,
   "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": 594.019,
       "eval_steps_per_second": 297.081,
       "step": 13
+    },
+    {
+      "epoch": 0.005669737774627924,
+      "grad_norm": 0.013973494991660118,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.9297,
+      "step": 14
+    },
+    {
+      "epoch": 0.006074719044244204,
+      "grad_norm": 0.014227038249373436,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.9289,
+      "step": 15
+    },
+    {
+      "epoch": 0.006479700313860484,
+      "grad_norm": 0.014232249930500984,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 11.9294,
+      "step": 16
+    },
+    {
+      "epoch": 0.0068846815834767644,
+      "grad_norm": 0.01532355509698391,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 11.9282,
+      "step": 17
+    },
+    {
+      "epoch": 0.007289662853093045,
+      "grad_norm": 0.01495895441621542,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9276,
+      "step": 18
+    },
+    {
+      "epoch": 0.007694644122709325,
+      "grad_norm": 0.012949861586093903,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 11.9292,
+      "step": 19
+    },
+    {
+      "epoch": 0.008099625392325605,
+      "grad_norm": 0.015499262139201164,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.9285,
+      "step": 20
+    },
+    {
+      "epoch": 0.008504606661941885,
+      "grad_norm": 0.016316721215844154,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 11.9294,
+      "step": 21
+    },
+    {
+      "epoch": 0.008909587931558166,
+      "grad_norm": 0.01622353307902813,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.929,
+      "step": 22
+    },
+    {
+      "epoch": 0.009314569201174445,
+      "grad_norm": 0.0137627013027668,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 11.9301,
+      "step": 23
+    },
+    {
+      "epoch": 0.009719550470790726,
+      "grad_norm": 0.015497871674597263,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.9295,
+      "step": 24
+    },
+    {
+      "epoch": 0.010124531740407006,
+      "grad_norm": 0.01868840865790844,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 11.9277,
+      "step": 25
+    },
+    {
+      "epoch": 0.010529513010023287,
+      "grad_norm": 0.012535473331809044,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9298,
+      "step": 26
+    },
+    {
+      "epoch": 0.010529513010023287,
+      "eval_loss": 11.92922306060791,
+      "eval_runtime": 7.0474,
+      "eval_samples_per_second": 590.143,
+      "eval_steps_per_second": 295.142,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6144393216.0,
+  "total_flos": 12288786432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null