Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12818e06a444005cb8daa14b2ac0a405804fe99ef5b9c9424c06206abc395e30
+oid sha256:918b1cab71ebba90a428579a7564e639298e83e6761374483f49644704075e7f
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30607522f232867bac8d14e1b2be8e9e9f8c363d27ac1486623f5b48b371ba3e
+oid sha256:2d5ef7870af310ef229829711dae4b6f79456d9e6f9e1492bbe28b604211baa4
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf00b0e01a47b4370d9bbd08cd1a3cde0d578a03c7ab0642cbadca70178368c
+oid sha256:5e05343cded05c60740d6de4c4834260b4a342f6ca5ef008d7c59110070d517c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e2dfd11e8b4f8902227d059aceef2ecbad8cd79e4a9868e5bda08e20d1d706
+oid sha256:21e2b5d9560191cd8cd454fd2be1d438284aac8617273afc89cbf21659e669ae
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5140562248995983,
+  "epoch": 0.7710843373493976,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -31,6 +31,21 @@
       "eval_samples_per_second": 31.917,
       "eval_steps_per_second": 4.256,
       "step": 8
+    },
+    {
+      "epoch": 0.642570281124498,
+      "grad_norm": 1.1430367231369019,
+      "learning_rate": 3.887395330218429e-05,
+      "loss": 1.9168,
+      "step": 10
+    },
+    {
+      "epoch": 0.7710843373493976,
+      "eval_loss": 1.222444772720337,
+      "eval_runtime": 3.2806,
+      "eval_samples_per_second": 32.006,
+      "eval_steps_per_second": 4.268,
+      "step": 12
     }
   ],
   "logging_steps": 10,
@@ -50,7 +65,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6401245833068544.0,
+  "total_flos": 9601868749602816.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null