Training in progress, step 3380, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1698d0b9850198369e888fcfaf13d37be26de99003ada18e391207f1b5ff228
+oid sha256:69537f9ed2ed65ee60acaac389fcecc462f045dfeb53ece12f3946f8b602575d
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8fe17bfb83911cb927d541d4a34d80b626c32a1c080df866cc26b5c30ec4ff1
+oid sha256:5eddb8d0942fc0d2111a643fd0b3d55490262a609cbee970570ebbd5ab507d8c
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db2bdbe63109eacd97a36be96f1c1369969403fe38eb6536eaee017f63bad8f
+oid sha256:2972df69961514cb9cbbc80a0a964c5c02518f3c97507a0353d5aad14f50d0a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d7c2d8201e8b73967831cd725d7a9e1ee970c8f0d997a055abf4549ddfa7435
+oid sha256:05b6fd6b8b38a7df2dd205c561b40fe74b7f319a01589a7a4797e47201a7e9a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2688,
+  "epoch": 0.2704,
   "eval_steps": 500,
-  "global_step": 3360,
+  "global_step": 3380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1183,6 +1183,13 @@
       "learning_rate": 2.852655480925828e-05,
       "loss": 3.5195,
       "step": 3360
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 36.46931076049805,
+      "learning_rate": 2.8505486295849884e-05,
+      "loss": 3.5451,
+      "step": 3380
     }
   ],
   "logging_steps": 20,
@@ -1190,7 +1197,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 7983843719970816.0,
+  "total_flos": 8025605646680064.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null