Training in progress, step 3960, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0aeaf21dfa25596d3e83291fdac7d22780924777e6b26386fda19e60f85953
+oid sha256:7889d14a2444a830b872f5e86d561143f2cbab0ea5ba81dbb788ecd497b6dc12
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adef023b0b0184db66b469a4b3d5b9622ecbb07244f5c52c41d3671dd322e40a
+oid sha256:7ef7e9ed4a471e46548d0b25542268f6f7e42b296dc835d21a4629297b643f8a
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31209e19cd1e43f15fe297600ccd65154a6150b1671600037426d3845125ba25
+oid sha256:94bb4d16678255f69acd3c6ad1f7e28dae58deeccef6c73a9ed3860161dd1747
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c28f06383bf072aeed87a869c461b8eda46a4fd1dbe3f64038b5a01c478bcad
+oid sha256:4aa728ff8dd68ad393219e062ef8c6a1fc7dc031ee553ad652965f2249179521
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3152,
+  "epoch": 0.3168,
   "eval_steps": 500,
-  "global_step": 3940,
+  "global_step": 3960,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1386,6 +1386,13 @@
       "learning_rate": 2.7858899370977123e-05,
       "loss": 3.589,
       "step": 3940
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 48.60535430908203,
+      "learning_rate": 2.783381823144452e-05,
+      "loss": 3.6398,
+      "step": 3960
     }
   ],
   "logging_steps": 20,
@@ -1393,7 +1400,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 9303592776990720.0,
+  "total_flos": 9350734873362432.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null