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:c572ac4d384a3fc5cc7aed7fa3d3be0451819e99c5ee3e04b7b20aced39c78fa
+oid sha256:f6a3c998de94abc67fbee95d8b2d69ac9ad3f7d0b0e9cb026855881010841232
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7034b2a46f4ba566680888eace569f40000648dc4196686a161268ecd9eb8606
+oid sha256:f8608622efe9031bc9ed0b754de2302e813446e69ce45f9be3c5d49a1bca5e60
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c171c2897ca9d2f89e7a6497a214756f9883df2e8fed753bb9125824302999f
+oid sha256:05ab0f96d910ec29ccaf274451f94a01bb1f9f7873169ad5878c5dcbf1ef8780
 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": 0.2180293501048218,
+  "epoch": 0.4360587002096436,
   "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": 17.552,
       "eval_steps_per_second": 2.227,
       "step": 10
+    },
+    {
+      "epoch": 0.33542976939203356,
+      "grad_norm": 4.020260810852051,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 5.2304,
+      "step": 20
+    },
+    {
+      "epoch": 0.33542976939203356,
+      "eval_loss": 3.8652100563049316,
+      "eval_runtime": 22.696,
+      "eval_samples_per_second": 17.712,
+      "eval_steps_per_second": 2.247,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.803763874103296e+16,
+  "total_flos": 5.607527748206592e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null