Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6383a994356d2d5807ca12d4ac064319e6dceecb77f7545dd8de5f9dd85bf414
+oid sha256:68535f6f1447ab83d46d4ad846ad48afcf5639f7a698421f6918c724ce77b497
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13223e3411fc2b15d19a767fdaea673c867083b3932de3662b372c127602ef6c
+oid sha256:5bef50ba737dbe2d3ec7220e9f909379009a79d8677a1908f6475a83a52b2971
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8d600d482e23e3ca867dd9393eea90ad7988cda5e7fe71bdb3e78ed1ae286c
+oid sha256:30b1caa877f06ae036337ce6addb7ca1327a7a08a85655f6d3ea458052e94992
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09934460158675405,
+  "epoch": 0.11176267678509831,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 7.134,
       "eval_steps_per_second": 0.894,
       "step": 72
+    },
+    {
+      "epoch": 0.10348395998620213,
+      "grad_norm": 3.280524969100952,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.684,
+      "step": 75
+    },
+    {
+      "epoch": 0.10762331838565023,
+      "grad_norm": 3.2250235080718994,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 0.572,
+      "step": 78
+    },
+    {
+      "epoch": 0.11176267678509831,
+      "grad_norm": 3.109015941619873,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 0.6377,
+      "step": 81
+    },
+    {
+      "epoch": 0.11176267678509831,
+      "eval_loss": 0.16160938143730164,
+      "eval_runtime": 171.1081,
+      "eval_samples_per_second": 7.136,
+      "eval_steps_per_second": 0.894,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0250129562022707e+17,
+  "total_flos": 2.2781395757275546e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null