Training in progress, step 3500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4e87ce60e95f334f9ec47b8fe54b1d82f5a5f7978130fdf8d944e15669723f
+oid sha256:49956faf6d374c68968a5ce7b6cad75ae6ecaaf9b6c1e44fa3b0c3e7ff27ed82
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff5ecb883ad6d1eb389c5edac5865f629316fc50eededfe70d565ad326e30b3
+oid sha256:8df6d00900b1e88654bd4ca60efe24abd89010ca1df7cdfd0f2ad54e52ea5cef
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f1c1e4927fa3815539e897f0308722f491e1900ce9959e8f01c6f5809d166d
+oid sha256:dbea88259d6e3921591759b6b112787854d664c6450349ec06e7cb329889ce0e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74901e7dfd1aad733e09f74ea6b7845fa91d24f912870eb55d586767f7c4065c
+oid sha256:b347a3fa18d78b1079ab69a462b88204415d2ec7a10bf5022f8a257be3147eb4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3891088962554932,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477231329690346,
+  "best_metric": 1.377625584602356,
+  "best_model_checkpoint": "./outputs/checkpoint-3500",
+  "epoch": 2.5500910746812386,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,13 +483,27 @@
       "eval_samples_per_second": 43.663,
       "eval_steps_per_second": 5.463,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.3617,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.377625584602356,
+      "eval_runtime": 143.5393,
+      "eval_samples_per_second": 43.709,
+      "eval_steps_per_second": 5.469,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.0244396170354688e+17,
+  "total_flos": 2.0839987895230464e+17,
   "trial_name": null,
   "trial_params": null
 }