Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1205743dbc4c301da388f39f4cbd22836e759477b2c2f3e7128292d73d548c8d
+oid sha256:fc650468491d5c442ef0192bdc9fda3030832acc1b2c66f91fe5e2a7380d7669
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3016165f0c6c461ebe01e702e7db990f9f0b6e031dfc0aba79ee968b250f34fc
+oid sha256:9a5038bc39d8fa9182d1aa11af9e86758e11ea82c1997bf549c776131cadc8ed
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b68fd37a48e3e687292158fa1099cf9a3e8146a4388e28bdd88071f71b6022fb
+oid sha256:7dcb27b4bb0ad94881133c9a57a78218473e5762ac58c9a86ac8ba3610caa0a9
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3993f1ade40b7ccc43179ee60d2b84e50c356bed8c82f5c7e7b3dedcbb9221a
+oid sha256:1c3c01b4feddd38ea5a7b98dbe35cafa9fe9e08cf11999502ba491f08017ee12
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5180491209030151,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 1.748633879781421,
+  "best_metric": 1.5037126541137695,
+  "best_model_checkpoint": "./outputs/checkpoint-2500",
+  "epoch": 1.8214936247723132,
   "eval_steps": 100,
-  "global_step": 2400,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,13 +343,27 @@
       "eval_samples_per_second": 43.726,
       "eval_steps_per_second": 5.471,
       "step": 2400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 1.4973,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 1.5037126541137695,
+      "eval_runtime": 146.268,
+      "eval_samples_per_second": 42.894,
+      "eval_steps_per_second": 5.367,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.4291504286643814e+17,
+  "total_flos": 1.4884411357237248e+17,
   "trial_name": null,
   "trial_params": null
 }