Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5917a623c31d8f73768c58ec3e7b9097790c44151639dc72dcbec05057bb3521
+oid sha256:b8638d1aec6d299346d3fe8f50131faa2c3b73c466c70d4c201430888555fd2d
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf952e60cc40bfd3300fcb28024ec793345f1a35c761ea499964bf6c7c67102
+oid sha256:6d1312735cc4d334a7dc28e951ba446062df4d66b9c42d8854f2123a3e2d3b31
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3c3e04f39a617235a8997802872984565e40f93fdc72257fb4514e5bbb6314
+oid sha256:6898f7cfc8c513f569f819ae2f0d2d8879521f0304cfc0f28a4a019543aabbec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03377110694183865,
+  "epoch": 0.0675422138836773,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 13.783,
       "eval_steps_per_second": 3.492,
       "step": 9
+    },
+    {
+      "epoch": 0.0450281425891182,
+      "grad_norm": 5.035146713256836,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.5712,
+      "step": 12
+    },
+    {
+      "epoch": 0.05628517823639775,
+      "grad_norm": 6.059263706207275,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.6058,
+      "step": 15
+    },
+    {
+      "epoch": 0.0675422138836773,
+      "grad_norm": 2.648972511291504,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.3104,
+      "step": 18
+    },
+    {
+      "epoch": 0.0675422138836773,
+      "eval_loss": 0.18601766228675842,
+      "eval_runtime": 16.4012,
+      "eval_samples_per_second": 13.719,
+      "eval_steps_per_second": 3.475,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6398499084042240.0,
+  "total_flos": 1.279699816808448e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null