Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eba031fc6935afacec18c63cf637bcaf133be6425691d9afdad41ebc8c28505
+oid sha256:562c177f06ae1571ed66ec12e77506b169db75bac1cd0a12a74a5d0bc28df835
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b384bfc9543fea82ff9ebf8ef270fac8ccd966ca490afce00b6c6d08e0d76099
+oid sha256:0caee660fd6e2662b4f3c59957638f0030f95787a3b8bbc24c0096ff3b44e51d
 size 63974

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": 0.010172143974960876,
+  "epoch": 0.02034428794992175,
   "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": 39.994,
       "eval_steps_per_second": 20.034,
       "step": 10
+    },
+    {
+      "epoch": 0.011737089201877934,
+      "grad_norm": 0.04390498623251915,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.7714,
+      "step": 15
+    },
+    {
+      "epoch": 0.01564945226917058,
+      "grad_norm": 0.04456234350800514,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.7622,
+      "step": 20
+    },
+    {
+      "epoch": 0.01564945226917058,
+      "eval_loss": 11.765852928161621,
+      "eval_runtime": 12.723,
+      "eval_samples_per_second": 42.364,
+      "eval_steps_per_second": 21.221,
+      "step": 20
+    },
+    {
+      "epoch": 0.019561815336463225,
+      "grad_norm": 0.057392362505197525,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 11.7654,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 660143996928.0,
+  "total_flos": 1320287993856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null