Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abefb5dbb7d74f27a49f3f66f13eb8932e56fedf94d48588dc96813b81668c5
+oid sha256:cd9bfe3a61b9d671b668afd9854e6e0f31dd1bfaf2c496e8b646c13b4b667b83
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff1a814809399bc31e3f44ea4a76d78c848700ab640abae1c3ec4538f4f8da77
+oid sha256:83d8eadc3f5112242fcda8091f4fe5bdcc4a798387065d67067a1d1908ed110a
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b671a8eca01cb9b6f4736829516f37a248a3b5268cb765ba18a2dd729fd3c17b
+oid sha256:91ce772f9b2a32aa1626e6ccbc135efad31ff1869adac26764a35a5c73bb1216
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
+oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.429054617881775,
-  "best_model_checkpoint": "./outputs/checkpoint-2200",
-  "epoch": 1.6029143897996359,
+  "best_metric": 1.4158506393432617,
+  "best_model_checkpoint": "./outputs/checkpoint-2300",
+  "epoch": 1.6757741347905282,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -315,13 +315,27 @@
       "eval_samples_per_second": 43.579,
       "eval_steps_per_second": 5.453,
       "step": 2200
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 1.4103,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 1.4158506393432617,
+      "eval_runtime": 143.8198,
+      "eval_samples_per_second": 43.624,
+      "eval_steps_per_second": 5.458,
+      "step": 2300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.3116148866861466e+17,
+  "total_flos": 1.3711720075820237e+17,
   "trial_name": null,
   "trial_params": null
 }