Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734330beaad492891ff5f7fc9df9a2e1b069f2c4211ce697c6855f1a02cdfc32
+oid sha256:8cf5df5f6d7116007c86a332272baa57bada46809920ed8d41b365a6337a903d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df4a54290fafb95c4a6d1e942a73c358bc2ff92a9bc5868ee328e710dde0905
+oid sha256:f573e1e96e5f6e7e61dbf7e18b488763536ac6c015331d6c287ce88a7ee83ed2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f0bd9d86319639dfe9833d26a1acc00818f50c46f354bc07ae5eca24846d97
+oid sha256:3107391da0b3a22e0d165a23f3350b25d47ba522f7f12c6917275276e0455593
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2876315116882324,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 1.2854410409927368,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 12.713,
       "eval_steps_per_second": 1.594,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 1.0456,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 1.2854410409927368,
+      "eval_runtime": 151.7702,
+      "eval_samples_per_second": 12.717,
+      "eval_steps_per_second": 1.595,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2745693497470976e+17,
+  "total_flos": 1.3385286781267968e+17,
   "trial_name": null,
   "trial_params": null
 }