Training in progress, step 260, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ef7c866d7d18cd44bc9d12177a548794d5c309ba0e4eedfd17449167d11b3b
+oid sha256:4c74abcbc22a956d2c4927f3cd90c498db1401577c1a95edd5aa2828ae826f3e
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a46c69917afb0de58ee2291c88b716000c1ddad671a41491530dcaa6e488cfd
+oid sha256:0405dd9af2f32c8a1a022354904e4a96c6491985948aa4e13d81d2e6b0537b10
 size 2423802

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e998aeb067d30d8950f7348a4d890bfd1791599ad6f3d5db56952d64809af4d
+oid sha256:1257d052b4a8dc172dc42140b2ee6a8793b59746e8cf14885edb0b6f2889582d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:549529bf2ef6166170cc78b313c10abe92d8424e01d3dbfc9bb2a483a33c5b1f
+oid sha256:1b9b1b69a7ab8ccbf3078c429a8961ade0793a75661dbafee0da970c8ab67482
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00018678060283439565,
+  "epoch": 0.00020234565307059528,
   "eval_steps": 500,
-  "global_step": 240,
+  "global_step": 260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,13 @@
       "learning_rate": 3.983333333333333e-05,
       "loss": 2.8566,
       "step": 240
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.688353538513184,
+      "learning_rate": 4.316666666666667e-05,
+      "loss": 3.0079,
+      "step": 260
     }
   ],
   "logging_steps": 20,
@@ -98,7 +105,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1154797709672448.0,
+  "total_flos": 1238496472055808.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null