Training in progress, step 2600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc650468491d5c442ef0192bdc9fda3030832acc1b2c66f91fe5e2a7380d7669
+oid sha256:e174e4e94a899beafa9c1bbe86f01c4feab4ec1f0be307efd28dfa83cacde37c
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a5038bc39d8fa9182d1aa11af9e86758e11ea82c1997bf549c776131cadc8ed
+oid sha256:f1d62ecbae204cca549314b1554c884304e78cc17e04037de064f77595c5ae7c
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dcb27b4bb0ad94881133c9a57a78218473e5762ac58c9a86ac8ba3610caa0a9
+oid sha256:9ed2e6e7194b18dd2ea9c5a73ce05b0eb8f0d9fc4df120db907ba6de9186dc94
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c3c01b4feddd38ea5a7b98dbe35cafa9fe9e08cf11999502ba491f08017ee12
+oid sha256:d7c5d3b3c2a8d9b140a1a8519d056f5ffffcb2bb6ee7238329a9e6866488adf2
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5037126541137695,
-  "best_model_checkpoint": "./outputs/checkpoint-2500",
-  "epoch": 1.8214936247723132,
+  "best_metric": 1.490273118019104,
+  "best_model_checkpoint": "./outputs/checkpoint-2600",
+  "epoch": 1.8943533697632058,
   "eval_steps": 100,
-  "global_step": 2500,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,13 +357,27 @@
       "eval_samples_per_second": 42.894,
       "eval_steps_per_second": 5.367,
       "step": 2500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 1.485,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 1.490273118019104,
+      "eval_runtime": 143.5853,
+      "eval_samples_per_second": 43.695,
+      "eval_steps_per_second": 5.467,
+      "step": 2600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.4884411357237248e+17,
+  "total_flos": 1.5480351852702106e+17,
   "trial_name": null,
   "trial_params": null
 }