Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d77cd3ad7eb3eb7afa0890364460da19064c86b45a8edfda3d1a6146dc307fc
+oid sha256:9103986efc96d921d7c447893c149eaa54dc9402200b47cc0a7d57445e68a82d
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c78b775f13348cc76975f21565c9e26870e2bac5c9800635dd50aa1796aa48c
+oid sha256:ab4498f5d3661daaffd40b12b49975922b4218434fb0d70f92bf0be60b0368e2
 size 63974

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": 0.0700454621990234,
+  "epoch": 0.1050681932985351,
   "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": 645.131,
       "eval_steps_per_second": 80.738,
       "step": 20
+    },
+    {
+      "epoch": 0.08082168715271931,
+      "grad_norm": 0.3623027205467224,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3582,
+      "step": 30
+    },
+    {
+      "epoch": 0.08082168715271931,
+      "eval_loss": 10.356002807617188,
+      "eval_runtime": 3.7996,
+      "eval_samples_per_second": 658.227,
+      "eval_steps_per_second": 82.377,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5379257794560.0,
+  "total_flos": 8068886691840.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null