Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0322cb1c844733bdabed9bf19b4c28b10ddc380b6e4a174abb86ff5e10529e
+oid sha256:321f481b8b4a58983b9f6624e65166552cb63280916a540d4755343cc7fd03fa
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59fd63a27b8636dbfe4ec67a5ff241b26092e9dbdfb6e5858f7aff7abd2d909b
+oid sha256:7a49c594da750c4aff7a997ff7c7a2056881bfe5f8e33ee1a99479f7ce2838e2
 size 151034501

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f87eeba1af718cddacd5d9616efe0fba785b21191a131136973f711b764cec
+oid sha256:8abc1651d90c08f1d53ebb2646d6c02484bede312b64b6066690c8bbd1412627
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3581469058990479,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 1.3450849056243896,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 1.092896174863388,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,13 +203,27 @@
       "eval_samples_per_second": 14.989,
       "eval_steps_per_second": 1.875,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 1.3321,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 1.3450849056243896,
+      "eval_runtime": 418.8093,
+      "eval_samples_per_second": 14.981,
+      "eval_steps_per_second": 1.874,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.539473771498373e+17,
+  "total_flos": 4.8636182340681216e+17,
   "trial_name": null,
   "trial_params": null
 }