Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d742f4f1595ee20efe17d0ac5aa90e245eff278670c7dec1e625d3c0f709a8c
+oid sha256:fc254380db18ef9e03a89daf645a5586631a157d1d06c72267e43f64086c0e5f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f1d264f262afd040af001c80f143841649dfdb44c697e75aeb5d9df49ed41c
+oid sha256:57f93acc85887a6284b34117ba37170f6f7939807e26d955b8842ed8d01d0bb4
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee72bd09c897a7f5e116ce252acd7632733fa6243262029b30575a43ee85c2a3
+oid sha256:c400d8725348b2cb960736157adb45bbbed9a27fd149b460f4c6a8ef61fcfc7c
 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": 0.03725422559503277,
+  "epoch": 0.049672300793377026,
   "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": 7.138,
       "eval_steps_per_second": 0.894,
       "step": 27
+    },
+    {
+      "epoch": 0.041393583994480856,
+      "grad_norm": 2.9004974365234375,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.664,
+      "step": 30
+    },
+    {
+      "epoch": 0.04553294239392894,
+      "grad_norm": 2.8733339309692383,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.5927,
+      "step": 33
+    },
+    {
+      "epoch": 0.049672300793377026,
+      "grad_norm": 3.473083019256592,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.6759,
+      "step": 36
+    },
+    {
+      "epoch": 0.049672300793377026,
+      "eval_loss": 0.19248369336128235,
+      "eval_runtime": 170.9492,
+      "eval_samples_per_second": 7.142,
+      "eval_steps_per_second": 0.895,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.593798585758515e+16,
+  "total_flos": 1.0125064781011354e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null