Training in progress, step 1040, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afbb78bc5d4f338b3de45927e37c2c7143ab5ee643dfe631e069fa92eb728523
+oid sha256:741f1e82263544b2af2ddd5880bd1151acdef154443223e1af5fa74c84fa4c5b
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6ec8ffdaba9ec2f7d78f345f8b8578b67c63fd524f95af3e96334c16310690
+oid sha256:c5e875a68f7de1135ec7eff6679cca0153967f574ae2078888d36849fcc7fa49
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e250fcc7dfce6fdffa6b0f011754c66243ad148deca4a5febf83c46786e5deaf
+oid sha256:09e6b49e9c75de37719a5ce5ce7ac22edb82ba14494ff3f8378eb2a2213d04a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1475ca4fa302f43b126c66f92deac3cab985ff0c7cf6532a7fd07ee716671370
+oid sha256:8540a59a904db0631e6ba6215ec79696a37252ba8141132429ae3f3eee3075b9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36493738819320215,
+  "epoch": 0.37209302325581395,
   "eval_steps": 500,
-  "global_step": 1020,
+  "global_step": 1040,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -823,14 +823,30 @@
       "loss": 0.4301,
       "num_input_tokens_seen": 680863,
       "step": 1020
+    },
+    {
+      "epoch": 0.3685152057245081,
+      "grad_norm": 0.27482128143310547,
+      "learning_rate": 0.0001262969588550984,
+      "loss": 0.4122,
+      "num_input_tokens_seen": 688582,
+      "step": 1030
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.438516765832901,
+      "learning_rate": 0.0001255813953488372,
+      "loss": 0.4253,
+      "num_input_tokens_seen": 695760,
+      "step": 1040
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 680863,
+  "num_input_tokens_seen": 695760,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.5310204475848704e+16,
+  "total_flos": 1.564518539870208e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null