Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bd723a82a3e2179d9478b331727447fa1ca5c87051a6025bfb970ebe967cb3
+oid sha256:df2f5e4234a5d82fc6363febb18f82cb8ad0a8406c7471f11ec652a7de92190f
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce873bcf540bdac7c4f991d80645511516f0a07356d5979d7f3a1024c4a97cc
+oid sha256:ae059cc95149f6958d58b2a33881ea11c42dc2a15e92bed9a21e1f62f40a42d8
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
+oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03201970443349754,
+  "epoch": 0.0480295566502463,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 632.997,
       "eval_steps_per_second": 79.139,
       "step": 20
+    },
+    {
+      "epoch": 0.03694581280788178,
+      "grad_norm": 0.3818082809448242,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 166.0408,
+      "step": 30
+    },
+    {
+      "epoch": 0.03694581280788178,
+      "eval_loss": 10.377680778503418,
+      "eval_runtime": 8.8119,
+      "eval_samples_per_second": 620.864,
+      "eval_steps_per_second": 77.622,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10753557528576.0,
+  "total_flos": 16168833515520.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null