Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75ea170e3816f4ca2bb07000f2ed8e249c16835adf9268059fed6bd23533a1e
+oid sha256:bea89a0aca0456c8e491b4a20e39f18cd350e019db6151165386ca0cf488fe4e
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2a29460a70268141b3ece4618536d4a0665b28a7e4370d3f42d0fdfaddf5e4e
+oid sha256:c5442ed4aecff44fa62fe3def53c0666982a82e48f4bcafa7d663c0fbfe95561
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ac2ce848992a96d8e3c8ad11a38658fb83c3bc2382c8a6c064530346900cbe
+oid sha256:231983afa907659f1652066fc762eed7adaf78a00475ebd1528076c8e4e7731f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007494275206439525,
+  "epoch": 0.009992366941919368,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 9.189,
       "eval_steps_per_second": 1.149,
       "step": 27
+    },
+    {
+      "epoch": 0.008326972451599473,
+      "grad_norm": 0.15783219039440155,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.3895,
+      "step": 30
+    },
+    {
+      "epoch": 0.00915966969675942,
+      "grad_norm": 0.17900213599205017,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.4093,
+      "step": 33
+    },
+    {
+      "epoch": 0.009992366941919368,
+      "grad_norm": 0.14911402761936188,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.3543,
+      "step": 36
+    },
+    {
+      "epoch": 0.009992366941919368,
+      "eval_loss": 0.3740505874156952,
+      "eval_runtime": 660.2612,
+      "eval_samples_per_second": 9.19,
+      "eval_steps_per_second": 1.15,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.732117285280154e+16,
+  "total_flos": 7.689425626595328e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null