Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa737ba6e1ba84b9ceecd09816b2c1a5186f4d1bbe8e3ff01be2085a4bd20f7f
+oid sha256:509c0d4cedc39a7d5f04e46393cd74eb9d4493e19ce2ac547c4b6af361a3a5ab
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:071ea6fc58a63f26fa4b63a6ea4e863606f1af18bbd834d26f859a775f1d396b
+oid sha256:00f9475d98a5a69c207f26315cfcf59b80d910ef69f9f66490768be95dffcdcb
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1befccf01f149621d991f2f9679547f90ac16ba56a4f828c659ef826349a56
+oid sha256:f5518b27092ab6aaacc0cc21ef2c162b93293f363ec7ec1be39604905ad54e10
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
+oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0460368394851685,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.42613636363636365,
+  "best_metric": 1.0355255603790283,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.5681818181818182,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 12.014,
       "eval_steps_per_second": 1.506,
       "step": 300
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002,
+      "loss": 1.1833,
+      "step": 400
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 1.0355255603790283,
+      "eval_runtime": 124.2488,
+      "eval_samples_per_second": 12.008,
+      "eval_steps_per_second": 1.505,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.682558365114368e+16,
+  "total_flos": 2.2452348635136e+16,
   "trial_name": null,
   "trial_params": null
 }