Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f344f50a80a0bc0dc011cd9c3d2d6045b4bd1803a855ea0066bedb9d678139
+oid sha256:18c49986d638844e59d81a84676ed14577443b6b38b8144c2376fcc3653058bc
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db39a09db19a5a861fcc8d9325620db973b11e445fa9f8f0c5639c5a066f9be
+oid sha256:45a2b9d529342642e23a88cf848020a9c526475581b16c9ee55101cb8632fb27
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9385acd159a025ccd0b5a01c24aef0bbaaa79b38d5e205d834949d4c26aa1a4c
+oid sha256:1ff0d769c62ca0f1dfcc5ff54753cf1287953c9fd82927f62dbef8fb59b714db
 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": 1.4471981525421143,
-  "best_model_checkpoint": "./outputs/checkpoint-300",
-  "epoch": 0.4,
+  "best_metric": 1.4266287088394165,
+  "best_model_checkpoint": "./outputs/checkpoint-400",
+  "epoch": 0.5333333333333333,
   "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": 30.762,
       "eval_steps_per_second": 3.859,
       "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002,
+      "loss": 1.5495,
+      "step": 400
+    },
+    {
+      "epoch": 0.53,
+      "eval_loss": 1.4266287088394165,
+      "eval_runtime": 47.1866,
+      "eval_samples_per_second": 30.75,
+      "eval_steps_per_second": 3.857,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0061246103552e+16,
+  "total_flos": 1.3414994804736e+16,
   "trial_name": null,
   "trial_params": null
 }