Training in progress, step 4500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6feb44fd4a371f3ab74ee5e57d06e2a75ac597305502b24b8d8f5195dde52e
+oid sha256:f8d3ecafc67bc6e2e47fa37822b8fb185cbcce87e25a128e8f81ebe119211ad5
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e3539775f402b4864f77f2f9b6ebf37e513ae8441a708b0d7377ff9f022dc4
+oid sha256:ad41f1cd24d383d923861c6374eb12efee562e4c6c8c823dab8c9d2f8cfe8bbc
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9eff77540dede028973a3a7d3de45171bd5bb15fa08b7884c1e9297e1e115a
+oid sha256:8e9002fc218558dac3fbced7f38dc0977f1e3296aa1ebf3b24f34ef5fe5ebf79
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae3d58e23bb299295105e102ba554966b77b6c0b683658ad76c5839a4c22e52
+oid sha256:74643c84b9992d45db76f51882ccf4816d015630d44f26180bcb4912f7bac463
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.798625214810185,
+  "epoch": 8.998593969692235,
   "eval_steps": 500,
-  "global_step": 4400,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -379,6 +379,21 @@
       "learning_rate": 7.066666666666667e-05,
       "loss": 1.2548,
       "step": 4400
+    },
+    {
+      "epoch": 8.998593969692235,
+      "grad_norm": 0.19095982611179352,
+      "learning_rate": 7e-05,
+      "loss": 1.2566,
+      "step": 4500
+    },
+    {
+      "epoch": 8.998593969692235,
+      "eval_loss": 1.1331112384796143,
+      "eval_runtime": 782.1504,
+      "eval_samples_per_second": 19.845,
+      "eval_steps_per_second": 2.482,
+      "step": 4500
     }
   ],
   "logging_steps": 100,
@@ -398,7 +413,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.867225477317132e+18,
+  "total_flos": 7.023300448505299e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null