Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177128138fa4d33a37bac233ad555bc2daebc47fd0624757a618d7d58ce2af4a
+oid sha256:f3fe8e7b6594d26ded13bbfa58bc14186890411cf10b53ea4f85abf7034d93f0
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4321198b235398d41571ef0bc4cf90406fe35356c0e51e85f74b617c9189962
+oid sha256:6015496f16faabaa3542b655edfe78dd073bbedd7b802add6971e011ec9530a5
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef2cd54db7aa44d7ce15aa60e17a159e954b389b719292da45c956fa837ba1d
+oid sha256:be7005cc3fc15acfdf82dddf063b2d2565e65e391024dc8176c777dcd11198a3
 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": 0.0009682524904571269,
+  "epoch": 0.0019365049809142538,
   "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": 112.023,
       "eval_steps_per_second": 56.011,
       "step": 10
+    },
+    {
+      "epoch": 0.0011172144120659157,
+      "grad_norm": 0.03296150267124176,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.934,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014896192160878876,
+      "grad_norm": 0.022446773946285248,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.928,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014896192160878876,
+      "eval_loss": 11.930259704589844,
+      "eval_runtime": 49.9116,
+      "eval_samples_per_second": 113.28,
+      "eval_steps_per_second": 56.64,
+      "step": 20
+    },
+    {
+      "epoch": 0.0018620240201098594,
+      "grad_norm": 0.020162925124168396,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 11.9292,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1536098304.0,
+  "total_flos": 3072196608.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null