Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f073ddbdf47ba2068025701aa32d5c54ebd60dcbb4d960803dc3e16859db7f3
+oid sha256:07c5d57c8f0d70ca706116e121388b3fe2b274f02bf39c33c17e778d6e65bcf9
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768952480bd95e80c37bf8c00bf129fcf0e57b1e2713a64a0d1dee54a0123901
+oid sha256:467d975348b6d16ae8bd98009a854eab0e063288a2eff4bc0ffb94bae397798c
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323bb1f1205a74bebd0f0bd9a8964d7b506928f6ead84ee656ba46045c26e2aa
+oid sha256:eb26646051d6ad9589b97bde1959db9d8644550abb439500c6e4a7bc67aad86d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3036551077788191,
+  "epoch": 0.3373945641986879,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 34.664,
       "eval_steps_per_second": 4.391,
       "step": 81
+    },
+    {
+      "epoch": 0.3149015932521087,
+      "grad_norm": 0.25220274925231934,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 1.9336,
+      "step": 84
+    },
+    {
+      "epoch": 0.3261480787253983,
+      "grad_norm": 0.24220967292785645,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 1.9553,
+      "step": 87
+    },
+    {
+      "epoch": 0.3373945641986879,
+      "grad_norm": 0.2649029493331909,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 2.0014,
+      "step": 90
+    },
+    {
+      "epoch": 0.3373945641986879,
+      "eval_loss": 1.9198718070983887,
+      "eval_runtime": 12.9953,
+      "eval_samples_per_second": 34.628,
+      "eval_steps_per_second": 4.386,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.649947204537549e+16,
+  "total_flos": 2.9381589850914816e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null