Training in progress, step 68, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c40abc5ddbc8cce4c38252033f65546ef0ed695d12c0979ab0e6e53b8ddff3d
+oid sha256:5a3ba91fcfa33a4fc60d7d960039c3cbbe3ab374b9c3163b3c0f9f4ea0bf01a5
 size 19552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6131a0b83a062e037bac2e68d74d4a9c1690df55d265b19520f04c71f8c51943
+oid sha256:23225fdb9d0919cbadab2d67e7a184b58ed35fe3def41e07f1e8c230e4d536fc
 size 44354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7bd16cd408bd3dd2676b8823dfc63738eec458eb445f09c19422fb33f5a1acb
+oid sha256:4b165213f53197ccef9210a316146efd985350a4587234352809bf283a32d781
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9fa892ecd236e652150058649b13d9161331d85e374c4bec1d60ad6a556c3a9
+oid sha256:40aaba2d15c70d89033b94214bc8306c06d04f2fbceef0fdedf952808109d707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03853418964865886,
+  "epoch": 0.05137891953154514,
   "eval_steps": 17,
-  "global_step": 51,
+  "global_step": 68,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -158,6 +158,49 @@
       "eval_samples_per_second": 36.066,
       "eval_steps_per_second": 4.512,
       "step": 51
+    },
+    {
+      "epoch": 0.04080090668681526,
+      "grad_norm": 0.018775586038827896,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 12.4476,
+      "step": 54
+    },
+    {
+      "epoch": 0.043067623724971665,
+      "grad_norm": 0.020082606002688408,
+      "learning_rate": 8.564642241456986e-05,
+      "loss": 12.4519,
+      "step": 57
+    },
+    {
+      "epoch": 0.04533434076312807,
+      "grad_norm": 0.01945601962506771,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 12.4513,
+      "step": 60
+    },
+    {
+      "epoch": 0.04760105780128447,
+      "grad_norm": 0.02504323236644268,
+      "learning_rate": 8.199842702516583e-05,
+      "loss": 12.451,
+      "step": 63
+    },
+    {
+      "epoch": 0.049867774839440875,
+      "grad_norm": 0.02477116324007511,
+      "learning_rate": 8.005405736415126e-05,
+      "loss": 12.4508,
+      "step": 66
+    },
+    {
+      "epoch": 0.05137891953154514,
+      "eval_loss": 12.448628425598145,
+      "eval_runtime": 61.7963,
+      "eval_samples_per_second": 36.086,
+      "eval_steps_per_second": 4.515,
+      "step": 68
     }
   ],
   "logging_steps": 3,
@@ -177,7 +220,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 111289565184.0,
+  "total_flos": 150133014528.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null