Training in progress, step 240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3078213dcd15bc291dc37ca3077f9efb155cb015e2ecfc039f1079c016cd9a50
+oid sha256:33ef7c866d7d18cd44bc9d12177a548794d5c309ba0e4eedfd17449167d11b3b
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684dc57c1e94460d88f7247e65733810667abcc8211761ae7f175a94fb2a5c38
-size 2423738
+oid sha256:1a46c69917afb0de58ee2291c88b716000c1ddad671a41491530dcaa6e488cfd
+size 2423802

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a160794c42b620b052ded8acee8ed084ab34b149aee53004744c1a7084b810
+oid sha256:1e998aeb067d30d8950f7348a4d890bfd1791599ad6f3d5db56952d64809af4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a258940d20544cb994c096c67b2810560f36bc1c5c956be9ea4d5468f6460551
+oid sha256:549529bf2ef6166170cc78b313c10abe92d8424e01d3dbfc9bb2a483a33c5b1f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00017121555259819602,
+  "epoch": 0.00018678060283439565,
   "eval_steps": 500,
-  "global_step": 220,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -84,6 +84,13 @@
       "learning_rate": 3.65e-05,
       "loss": 2.8568,
       "step": 220
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.0859078168869019,
+      "learning_rate": 3.983333333333333e-05,
+      "loss": 2.8566,
+      "step": 240
     }
   ],
   "logging_steps": 20,
@@ -91,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1070150797246464.0,
+  "total_flos": 1154797709672448.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null