Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4988ee20b81d3a46e329072303e5627b3c1a7f54562807f3e856f9eb8b3fac16
+oid sha256:d3492d5530b02835c9531ef75b23f3427a1c7c69988c94ea0775c41be2766f0b
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f75faf38dcf8230e20b4ba092c9535dba57f49e468c316decf7a8cb5c005c7
+oid sha256:8b4610eac08e58ab45a8d0da7a57f158c8a628c2415e899ae24140718a9c078e
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f02e514b4e5c13f44b14ad7feaf676d277151a50af4ad1e832f008ef0e6ce5
+oid sha256:8d379d03c31702ee3bd44da5515074e290a946a23244bff4456c43f7f41b5945
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2213743b4f875916581fc5443cc26d59196701491a910eff859c9efaa9616d17
+oid sha256:927bf77ece90acb8a3b2d256745a02ec2036360b33c6ccb0b6dcec32582ee2ee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2,
+  "epoch": 1.5,
   "eval_steps": 3,
-  "global_step": 12,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,6 +75,21 @@
       "eval_samples_per_second": 14.024,
       "eval_steps_per_second": 2.475,
       "step": 12
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.9127976298332214,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8639,
+      "step": 15
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 1.0964289903640747,
+      "eval_runtime": 1.2142,
+      "eval_samples_per_second": 14.001,
+      "eval_steps_per_second": 2.471,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -94,7 +109,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.684049411702784e+16,
+  "total_flos": 2.1106160173056e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null