Training in progress, step 5820, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f6bee707bd16994812f4ab6abe0b76396f1fcd5a795587aa16fd0375503283
+oid sha256:8f2d12c00c3910f5c8aadf1c3043d575f58f0e94d4e1904af9295d91088e5ba8
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a78778227fc0abc34ed31ed4cde0a6bd77af35f8cb0ff481a8a83ef11c522ed
+oid sha256:2f018a91942bfac6141fce26126b81cc10d8b6d03258988a8ed48ad7a147fb9c
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d955c232a1730a709d883a685c93094aec6c22aa6fdd94806aef697f010076
+oid sha256:73ca75c8c20354aa6121b583b0e2d1196548a9e950e5c54e2824364c1617a488
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27226a26f79ee380c55eb9253588111984d20dcd9f4210cd93f6516c9d906461
+oid sha256:ffeee657eab485848cc5e4a398e8908b8f07d67a077ba1a196eb593774ff8630
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.464,
+  "epoch": 0.4656,
   "eval_steps": 500,
-  "global_step": 5800,
+  "global_step": 5820,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2037,6 +2037,13 @@
       "learning_rate": 2.4988728375175216e-05,
       "loss": 3.5436,
       "step": 5800
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 40.504127502441406,
+      "learning_rate": 2.495243304591236e-05,
+      "loss": 3.561,
+      "step": 5820
     }
   ],
   "logging_steps": 20,
@@ -2044,7 +2051,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.3734753000456192e+16,
+  "total_flos": 1.3779205011996672e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null