Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45300c49b2c9acf8905d9ab5dadec2184e8efefb840d77cfa34aed8659e7f8ff
+oid sha256:3aa765bd4ba448071fb5280d8b7811f7c9a08c03fe98614bc90194f4dc800e99
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced67eeca63e60c98d6c64aa10109d9aff27081b763b85103eeb4a0bc4899e1b
+oid sha256:af5bedeee2c45881ea31da03f11ff4e04a8e3c50404fa47bcb6b89adfe27eca6
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0634b79427ffd6d4ab70a960890d62996d62c36b5f34ed12a9101043d0c7ea
+oid sha256:971d18b1498661ca2e478d94cee70958977c8629bc91870f6a60546d5625409b
 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": 0.06636885768985322,
+  "epoch": 0.13273771537970644,
   "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": 38.188,
       "eval_steps_per_second": 4.773,
       "step": 10
+    },
+    {
+      "epoch": 0.1021059349074665,
+      "grad_norm": 0.06684104353189468,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.5841,
+      "step": 20
+    },
+    {
+      "epoch": 0.1021059349074665,
+      "eval_loss": 0.5628232359886169,
+      "eval_runtime": 34.3843,
+      "eval_samples_per_second": 38.39,
+      "eval_steps_per_second": 4.799,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0640946295209984e+16,
+  "total_flos": 2.128189259041997e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null