Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55253205b265429c4329d889be58663da122889fae1be1af323faa4cdd2a55b
+oid sha256:9062d82bf6c01714a8bc139e57048e0a1408dd46d29692e4adfab81c12c11212
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a90c559550d2478dede85e57d6af776ad0c7c350ac3363096a03cdc0c718e0a0
+oid sha256:3239a64ba59b650079a5eeb1487a17c6f209297a21c5a4da5197a9ef2106bf89
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c037384a9cbc8581bd2019de705fcab8ab427ff19cd49f03b529c50a205a6a
+oid sha256:70168052704796a5abb9d0b9c508a9b89ab3a8963fa20bba019e60bdebdc9e90
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
+oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3619952201843262,
-  "best_model_checkpoint": "./outputs/checkpoint-2700",
-  "epoch": 1.9672131147540983,
+  "best_metric": 1.3511581420898438,
+  "best_model_checkpoint": "./outputs/checkpoint-2800",
+  "epoch": 2.040072859744991,
   "eval_steps": 100,
-  "global_step": 2700,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,13 +385,27 @@
       "eval_samples_per_second": 43.644,
       "eval_steps_per_second": 5.461,
       "step": 2700
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002,
+      "loss": 1.331,
+      "step": 2800
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 1.3511581420898438,
+      "eval_runtime": 143.762,
+      "eval_samples_per_second": 43.642,
+      "eval_steps_per_second": 5.46,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.60955611905024e+17,
+  "total_flos": 1.669167753668444e+17,
   "trial_name": null,
   "trial_params": null
 }