Training in progress, step 21, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd030c5ed2843ec05e5fb277d77bdde344e3f12c7d3870609acb84e845d264f2
+oid sha256:f880a4e1745d49b7c45949a05153ccf8f4b045a811d84958cd4abc00fac67dbd
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2948c5dbc51bae5cb4e4976835544332c592fb9db305363cf3ff4068df714bbb
+oid sha256:d65e185024af1ce05fbcb06b6e277c2b33368b7855ab77859f026375accaec2a
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb05f0d759ae1c790e4c31eb74d4a60bc985859785fc219ddf4992451dd0252
+oid sha256:e99829502e75e5e0810e799113406f096b1811b4de5e7bf230e8c2ba6819dcef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d238195ca09ed8cbcd3cc35f5a395bf6b3bc853a4c8c7d3f2134fd9d41f2760
+oid sha256:83450c18b224a87d74f8c8e7d50fafb72f4e677fe1089fb566389ff9d23f9b65
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5319148936170213,
+  "epoch": 1.7872340425531914,
   "eval_steps": 3,
-  "global_step": 18,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,21 @@
       "eval_samples_per_second": 48.16,
       "eval_steps_per_second": 7.224,
       "step": 18
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 2.895676851272583,
+      "learning_rate": 6.19657832143779e-05,
+      "loss": 2.6033,
+      "step": 21
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "eval_loss": 2.7672295570373535,
+      "eval_runtime": 0.4158,
+      "eval_samples_per_second": 48.098,
+      "eval_steps_per_second": 7.215,
+      "step": 21
     }
   ],
   "logging_steps": 3,
@@ -124,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3603476219166720.0,
+  "total_flos": 4204055589027840.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null