Training in progress, step 200

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:395efb7ac92feb47eaf1520932442cb0cc9e35ebc4778caf7da6505df0d8b992
+oid sha256:718f0f4a4a30dd3f0cde28288176afe0918331ca66b83266c2c7b86ab75f1954
 size 109098378

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:395efb7ac92feb47eaf1520932442cb0cc9e35ebc4778caf7da6505df0d8b992
+oid sha256:718f0f4a4a30dd3f0cde28288176afe0918331ca66b83266c2c7b86ab75f1954
 size 109098378

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e135a2352bdbc7afabc8132cf4537df96216fdc4bac44afc895632e534e00150
+oid sha256:a339dba30dee56abb900b4b5b6275b0e72bddd7d8fdfa5f73566b0a197f94fb1
 size 218180026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7aae06433d36dec01576e0562f36b4076fb1fee74c8c3fe9612fb4a8d7ca539
+oid sha256:36d79b2d10d91cebf45b05cd8501a7b1c2f8655c5a67a7c9ad5735eaef97179b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f7b7ba597213d5cb540cbd80cea65d7d686972c4f3df4d2b2b78618ad9d474
+oid sha256:a6c551242cc75b2a1af1150159544dd6d1b7ce6d8c49d2dd2235847aeaabdce9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015091410831321146,
-  "global_step": 175,
+  "epoch": 0.0017247326664367024,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -104,11 +104,25 @@
       "eval_samples_per_second": 1.505,
       "eval_steps_per_second": 0.752,
       "step": 175
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.9999961080047352e-05,
+      "loss": 0.2259,
+      "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 0.1998293548822403,
+      "eval_runtime": 66.4429,
+      "eval_samples_per_second": 1.505,
+      "eval_steps_per_second": 0.753,
+      "step": 200
     }
   ],
   "max_steps": 115960,
   "num_train_epochs": 1,
-  "total_flos": 3528446682071040.0,
+  "total_flos": 4003314210816000.0,
   "trial_name": null,
   "trial_params": null
 }