Training in progress, step 4100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a2c16a2bd957739cf49d4202da78be14a39991edf7639e0189fb1046af80a0
+oid sha256:9ae8f78837a20ee5c978c2a077755f16f3c7a48728bf0735a90d0e1cd83bf3a5
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7cc64f356044843662be551cc67adbea6efe273615e55e55670b317c6c56d7a
+oid sha256:db72bdd04140f566c62ccb4eb7f8164308eab903d1957aec74ebb8dc082efbed
 size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c4fc3aea8f41e09e4cc39bb86d7c3486439d67281d7488abaf1e73b80986f3
+oid sha256:b3e0b5e96cc759ca2993321a29bcb97dc47920a94669e00d8ed217a0a629b63f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab644d38b64875fe4b9db6a2dd788efbee5d9e5dadfabf0dd125e8dae428442
+oid sha256:1ef51ed05818f33aebca9592cb64baf0df006aad2a34a7cf944f4a48b70afce3
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.314718246459961,
-  "best_model_checkpoint": "./outputs/checkpoint-4000",
-  "epoch": 2.914754098360656,
+  "best_metric": 1.299881935119629,
+  "best_model_checkpoint": "./outputs/checkpoint-4100",
+  "epoch": 2.9876138433515482,
   "eval_steps": 100,
-  "global_step": 4000,
+  "global_step": 4100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,13 +567,27 @@
       "eval_samples_per_second": 47.113,
       "eval_steps_per_second": 5.895,
       "step": 4000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0002,
+      "loss": 1.2922,
+      "step": 4100
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 1.299881935119629,
+      "eval_runtime": 133.2671,
+      "eval_samples_per_second": 47.078,
+      "eval_steps_per_second": 5.89,
+      "step": 4100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.3813221997007667e+17,
+  "total_flos": 2.4410408101719245e+17,
   "trial_name": null,
   "trial_params": null
 }