Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4109bd90fc7f5faa7fcede643834039b1747084b7591137960b86d099817b2c
+oid sha256:757e659bf33071c096568d8eb06785568c67acd861a7092274d741368be256e6
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032c7c5d1b22e401f78fa7173ec4007107011910cac95f55d965c293810824d3
+oid sha256:b6b7a3c33e9598887c6963727785f726eec8c742c06af36409d4283905c1d83c
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2511746767caf74ed2af043be349b91a9f9de694b3b61fb6953cef602c3b33a
+oid sha256:613209fe19785aab62e1f8fb807af95ea3ab972ed7fc7b2d61958367dc06f82c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
+oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.298874855041504,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 1.384335154826958,
+  "best_metric": 2.2830755710601807,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 1.4571948998178508,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,13 +273,27 @@
       "eval_samples_per_second": 30.629,
       "eval_steps_per_second": 3.832,
       "step": 1900
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002,
+      "loss": 2.2724,
+      "step": 2000
+    },
+    {
+      "epoch": 1.46,
+      "eval_loss": 2.2830755710601807,
+      "eval_runtime": 204.6478,
+      "eval_samples_per_second": 30.658,
+      "eval_steps_per_second": 3.836,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.419260380362752e+16,
+  "total_flos": 5.70422421531648e+16,
   "trial_name": null,
   "trial_params": null
 }