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:dceaa66676f15994dd65a13d1925419a43c67d7d4dc0fc8039578d87bc790598
+oid sha256:529254a4d9786a97e90da4397d1ac996dd0c8abc764cf9fedbbb700c22015040
 size 1134088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f3e536d295d9df6514af6917d0ec07f7e7d74a8aabc2a5dc793e036a085276
+oid sha256:cd75f4bc5dc6fb896acf6dad9db6b72eb321fa1533b91db159d9dbb55dec8d44
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb34a1b2d6aaa4306f374478d73bfa9b1d60dbea8092f9ab442eb96d6e23eb6
+oid sha256:12b7b3c5e0224a100d07790dce638f6ef26ebe7a218168fc915f411741c3a42f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18654708520179372,
+  "epoch": 0.37309417040358744,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 330.845,
       "eval_steps_per_second": 41.532,
       "step": 10
+    },
+    {
+      "epoch": 0.28699551569506726,
+      "grad_norm": 1.4584089517593384,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.9772,
+      "step": 20
+    },
+    {
+      "epoch": 0.28699551569506726,
+      "eval_loss": 1.8149807453155518,
+      "eval_runtime": 1.4797,
+      "eval_samples_per_second": 317.639,
+      "eval_steps_per_second": 39.874,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 431025429676032.0,
+  "total_flos": 864200612118528.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null