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:e8fe5085b89050821a6c5389617d5ee2fa3ebb46d67b6541275b1fb73e75ec2c
+oid sha256:3a2580d8ec1612540103e7d1d43cb90d4ebdec1282fe51f10457204905d4700e
 size 75507072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e311cfcff94b8adf42c708077dbf0ca4e304dba7408fa16243e7f627e87ac24
+oid sha256:13e3ba78a38f66155720e7c13f812c2a4346d506d612c4b526e7ee4f40b88310
 size 151032837

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c459a2c8cc316df8cc4f80f04b42cf96413340513e5446d85ab7d7620edec535
+oid sha256:0df161def7cd001c4c87cef77ffd46a655436a9551b23f43fa5264ada38a0aff
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3309524185001782da002e1efb7406e18966db2aee795c24a16a9ee18dd8d0
+oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1538294553756714,
-  "best_model_checkpoint": "./outputs/checkpoint-3400",
-  "epoch": 2.477959927140255,
+  "best_metric": 1.1433058977127075,
+  "best_model_checkpoint": "./outputs/checkpoint-3500",
+  "epoch": 2.550819672131148,
   "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": 18.349,
       "eval_steps_per_second": 2.296,
       "step": 3400
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.0002,
+      "loss": 1.1227,
+      "step": 3500
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.1433058977127075,
+      "eval_runtime": 342.1437,
+      "eval_samples_per_second": 18.337,
+      "eval_steps_per_second": 2.294,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1024573457611305e+18,
+  "total_flos": 1.1348327186771313e+18,
   "trial_name": null,
   "trial_params": null
 }