Training in progress, step 1280, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6083d1472c6086310a747e55e3c219fd918f02590a78870e05c736cd45dbab7
+oid sha256:0d5067b1a890360f337cf6445bbde7702bf4d94ba19dcbad5ec3fde5ed47b77b
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381cacd46391e3f555d4e12d200333abae360d4bdef760f00cdb360a10db7906
+oid sha256:221a3c11dc01f47bbfd2f4679f77f9469ee258a3a5acd5d4d4ab58e32b9cc65b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fca463d79bf4813a9d6530d90204c4d73a7f2230eb606726b7385a62bc76294f
+oid sha256:2dffb25eadcc0c14a11d06ce2959da02a95556098d9b1b694401b6585e76c1de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53516e58e5e8a23d810a2b934d82c13e25c739e42ae684ed7376620ab310e104
+oid sha256:56c936539488437eac974e0855f3113cbe40b51763be54460e94d4c5de858482
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.45080500894454384,
+  "epoch": 0.45796064400715564,
   "eval_steps": 500,
-  "global_step": 1260,
+  "global_step": 1280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1015,14 +1015,30 @@
       "loss": 0.4169,
       "num_input_tokens_seen": 848238,
       "step": 1260
+    },
+    {
+      "epoch": 0.4543828264758497,
+      "grad_norm": 0.36439695954322815,
+      "learning_rate": 0.00010912343470483007,
+      "loss": 0.4131,
+      "num_input_tokens_seen": 854482,
+      "step": 1270
+    },
+    {
+      "epoch": 0.45796064400715564,
+      "grad_norm": 0.4523600935935974,
+      "learning_rate": 0.00010840787119856887,
+      "loss": 0.3947,
+      "num_input_tokens_seen": 860605,
+      "step": 1280
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 848238,
+  "num_input_tokens_seen": 860605,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.9073877159112704e+16,
+  "total_flos": 1.935196731638784e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null