Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cdb2d2bd383f9d682773ba18b3d650b8d86c24807263b460101d104990b5fbd
+oid sha256:4dbb5ec17dc6c745a0958083e2e6bc5416ecde6983c0851592cc9e25657db424
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64c136729e239fcf9d475917514a3c85efe9d6d2a9042f14f52bc0da45959199
+oid sha256:ef679d441414e6c33e453c66ea5f96401c07f2003d90fe960244ee38eb8d2246
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ea83940ca57b6ef197c4f2ea03f79aae4bea217693ebee91420b20a7417c9
+oid sha256:980556105c838238e4bff9f061afe997b1bb238013e8dd9a40bbbded893a0389
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7612203359603882,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 0.8743169398907104,
+  "best_metric": 1.730454921722412,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 0.9471766848816029,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,13 +175,27 @@
       "eval_samples_per_second": 11.321,
       "eval_steps_per_second": 1.417,
       "step": 1200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 1.7685,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.730454921722412,
+      "eval_runtime": 554.4409,
+      "eval_samples_per_second": 11.316,
+      "eval_steps_per_second": 1.416,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.124074497483735e+17,
+  "total_flos": 3.384096572941271e+17,
   "trial_name": null,
   "trial_params": null
 }