Training in progress, step 880, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f753704d109104bb1125acdcf9f12fbef1f885465c235982ef55d3483c6c1ca
+oid sha256:10e278fe75c0875651454a628fb5081e25c9b4eddb980049aa53d473f22d3859
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fbd5a1b2192a61e59afc6b4488ed6f766d9a0afb1feca701f1e7b429578040a
+oid sha256:04ed5db3d6a74db1fc85886f2b7a625f5118fae9676ddbbe7eb972f86ea748ae
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b60b57d0860f7eb0d93725cd9d5ecb3ff80ada40fb4afc24fe2f8b4a881ff8
+oid sha256:57d455a0341a2c5c31eede937d31408b4b0a31f087c401955643a52ffd75f76a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97d83983c29fc1de97a46291eb4bee37025918a13b0d08e696a566dd59b594e
+oid sha256:cf5b23a851e345e8e4081674591dcebfd10a22b109ff1badb1c585816cbde3fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3076923076923077,
+  "epoch": 0.3148479427549195,
   "eval_steps": 500,
-  "global_step": 860,
+  "global_step": 880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -695,14 +695,30 @@
       "loss": 0.4365,
       "num_input_tokens_seen": 574126,
       "step": 860
+    },
+    {
+      "epoch": 0.3112701252236136,
+      "grad_norm": 0.31020838022232056,
+      "learning_rate": 0.00013774597495527728,
+      "loss": 0.4076,
+      "num_input_tokens_seen": 581039,
+      "step": 870
+    },
+    {
+      "epoch": 0.3148479427549195,
+      "grad_norm": 0.2839311361312866,
+      "learning_rate": 0.00013703041144901611,
+      "loss": 0.4139,
+      "num_input_tokens_seen": 587384,
+      "step": 880
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 574126,
+  "num_input_tokens_seen": 587384,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.2910066276036608e+16,
+  "total_flos": 1.3208191876841472e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null