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:d191980d7e011eabcf83a0d05f8ee032e64e0c005a8a2f0622203291e579d5d1
+oid sha256:bb27add6e59d1ab1779f9c76f19d32afbd5a70d126ac25c65da940b5198c3cc3
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2885e123662980ef740ad9c8bd24d87373f837193839ecd74935567bb53ca68f
+oid sha256:54a696d480d93cffdc678727bb3b925c6a9ab17953968f8aa20f6ab9cabf1efc
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
+oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
 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": 0.0030627871362940277,
+  "epoch": 0.006125574272588055,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 162.007,
       "eval_steps_per_second": 81.003,
       "step": 10
+    },
+    {
+      "epoch": 0.0035339851572623393,
+      "grad_norm": 0.427160382270813,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 41.4984,
+      "step": 15
+    },
+    {
+      "epoch": 0.004711980209683119,
+      "grad_norm": 0.43340450525283813,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 41.5071,
+      "step": 20
+    },
+    {
+      "epoch": 0.004711980209683119,
+      "eval_loss": 10.37428092956543,
+      "eval_runtime": 11.1192,
+      "eval_samples_per_second": 160.803,
+      "eval_steps_per_second": 80.401,
+      "step": 20
+    },
+    {
+      "epoch": 0.005889975262103899,
+      "grad_norm": 0.39236587285995483,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 41.493,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 667285192704.0,
+  "total_flos": 1334570385408.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null