Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a8501e47e0f7c194af5aa1ce00b5883ec69a70d0cd7fd80dc4474f84e26a89
+oid sha256:d491b3645ea5684ae9b55f454d022425dc48c87500babba9ed0dd46116207f00
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0bea142d2811f45ef9d69a5ae2b39c76cc97310305e21dcfb9d9c79e2db986
+oid sha256:846cb220930a00172b131504817db4123a3175645bdf99d7538df8e3c6cfda35
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
+oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
 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": 0.003058643609199459,
+  "epoch": 0.006117287218398918,
   "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": 13.616,
       "eval_steps_per_second": 6.808,
       "step": 10
+    },
+    {
+      "epoch": 0.0035292041644609143,
+      "grad_norm": 2.0198276042938232,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.8499,
+      "step": 15
+    },
+    {
+      "epoch": 0.004705605552614552,
+      "grad_norm": 3.1428215503692627,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.0307,
+      "step": 20
+    },
+    {
+      "epoch": 0.004705605552614552,
+      "eval_loss": 1.6161822080612183,
+      "eval_runtime": 131.4252,
+      "eval_samples_per_second": 13.62,
+      "eval_steps_per_second": 6.81,
+      "step": 20
+    },
+    {
+      "epoch": 0.00588200694076819,
+      "grad_norm": 1.708250641822815,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.2073,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2136113493835776.0,
+  "total_flos": 4272226987671552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null