Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f81d0331058633c3c462bca5761f09528ff4e84b03bc9d3d09b08ff4ee28523
+oid sha256:55cb8be523cc641687d9a4362722a0a623c3269ed03e1aad89718ca52bf502cb
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f243766adadcb040df645a9a8372911e6da84db5fa14434966bec257173a2ad7
+oid sha256:b1813e91f2cfa1eb270c88b0b78abf1bdd57d56bae4a2de331b9a13e01894d9b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e878fc0fbc86334888140425f50a172daf0ca6c9b8e00f870566985c8b9eac8
+oid sha256:a5276bfff6a9f44b6571a60e5907a8f84a8585a1992ad727c0bb7ed37a25fe20
 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": 2.3840975761413574,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 2.3692121505737305,
+  "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": 30.633,
       "eval_steps_per_second": 3.833,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 2.3425,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 2.3692121505737305,
+      "eval_runtime": 204.8938,
+      "eval_samples_per_second": 30.621,
+      "eval_steps_per_second": 3.831,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.994021987006464e+16,
+  "total_flos": 4.279485281605632e+16,
   "trial_name": null,
   "trial_params": null
 }