Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76536dee9747dec8dd1f3f3ccd41b7a1b9b67ceb8b29368eb6f6a461902249e1
+oid sha256:fb078275f5fa91778de46581f3f5dad176d10df12ee7923c2f1c1ff15c003d4c
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c49e4cfc2242be4175f2532f1dca5492fae7031c7b3a956c83903e4d55b47c
+oid sha256:0d18349d213872df6b0ef49f521349d64dfb6bc666a9ff93f11aa0b79376c868
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec38c457da9a42258377534f1711dd182dc95cdf22873640757de0b8ac5fc68
+oid sha256:e7b2c53f529a62a0884f6998e7f192527c1a4b1a76b45c95aa4b317f0f9f4397
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a78e728336b77d3305afe2734acb1241c76f8f2c33b35460bc07397abc49ba2
+oid sha256:bd37581d93a41fc457d899cacb7a67009a6909f6dbf72b467de55158ef91ac94
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4019700288772583,
-  "best_model_checkpoint": "./outputs/checkpoint-2400",
-  "epoch": 1.748633879781421,
+  "best_metric": 1.3896080255508423,
+  "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": 43.621,
       "eval_steps_per_second": 5.458,
       "step": 2400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 1.3815,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 1.3896080255508423,
+      "eval_runtime": 143.8457,
+      "eval_samples_per_second": 43.616,
+      "eval_steps_per_second": 5.457,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.430781883693056e+17,
+  "total_flos": 1.4901757565064806e+17,
   "trial_name": null,
   "trial_params": null
 }