Training in progress, step 3600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0445650b673f6acf4b81accd31266f2c4637fc19aa77cc6e396eaa4975a1eab
+oid sha256:55634c5d7a040a75ce54fb2d704473146db76bf9289ba6738a6f081f400e5b95
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286fd08dd930b8bfdfaa5d84780012e0686a79b98621af42af734f8c4f1c5e8d
+oid sha256:148c62c2eda7a65556b9f87791af7d8a3e04eeef8595750094f699ff268fc9d9
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330a75bddc9a21e822cfc3670609e9a673a0ce82e6de4caea030d25bd7d00980
+oid sha256:e007e17a1b1c7e56e3884c6888dacdf75718f5d9d333760d3458421fdaac671a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f466e63f2d702a9646f61d3cb0499d7a443ca833cfea51694a53eaa24cfd01
+oid sha256:43e3cf8d56a3f083d00cc85544d76ada2f884a1018c8752332d96f2799911117
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.221109390258789,
-  "best_model_checkpoint": "./outputs/checkpoint-3500",
-  "epoch": 2.5500910746812386,
+  "best_metric": 1.205322027206421,
+  "best_model_checkpoint": "./outputs/checkpoint-3600",
+  "epoch": 2.6229508196721314,
   "eval_steps": 100,
-  "global_step": 3500,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,13 +497,27 @@
       "eval_samples_per_second": 11.293,
       "eval_steps_per_second": 1.413,
       "step": 3500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0002,
+      "loss": 1.1428,
+      "step": 3600
+    },
+    {
+      "epoch": 2.62,
+      "eval_loss": 1.205322027206421,
+      "eval_runtime": 555.5155,
+      "eval_samples_per_second": 11.294,
+      "eval_steps_per_second": 1.413,
+      "step": 3600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.112777792001802e+17,
+  "total_flos": 9.372837614940979e+17,
   "trial_name": null,
   "trial_params": null
 }