Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3492d5530b02835c9531ef75b23f3427a1c7c69988c94ea0775c41be2766f0b
+oid sha256:5636f3b761cc83cc2a2a45389dffacd70aadc3271d647aac1fe0e48e504aec76
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b4610eac08e58ab45a8d0da7a57f158c8a628c2415e899ae24140718a9c078e
+oid sha256:e3f067aa41281509eb10fb3673e471b0a928bcb13b603abb4dd0c1cf0551d8bf
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d379d03c31702ee3bd44da5515074e290a946a23244bff4456c43f7f41b5945
+oid sha256:f8155c1b7f0bff45feb959910ee9688e108c82d7027b767cbf88790296dcf35b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927bf77ece90acb8a3b2d256745a02ec2036360b33c6ccb0b6dcec32582ee2ee
+oid sha256:75358b65e2b92f301729a22a08ee55a5718f5dc35950f9271c26aacc1fec4005
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5,
+  "epoch": 1.8,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,6 +90,21 @@
       "eval_samples_per_second": 14.001,
       "eval_steps_per_second": 2.471,
       "step": 15
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.0147470235824585,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.8137,
+      "step": 18
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 1.1079833507537842,
+      "eval_runtime": 1.2155,
+      "eval_samples_per_second": 13.986,
+      "eval_steps_per_second": 2.468,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -109,7 +124,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1106160173056e+16,
+  "total_flos": 2.537182622908416e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null