Training in progress, step 360, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80dbb1c54c0d5b697ffb1db9777ecd0e4186f5de71249b858bcf512f10de7aee
+oid sha256:cc49fc34045419f2a9dace17402a22103368094c6a2987a1616d0e939d14e164
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f943a705f415cf465b2a80496bdaa14239fc12e3961065fffdc8ba616e9619
+oid sha256:23a88e35eeb6b5fa8d07251e65fe421367b7e6e5c40b58ad1d552622a1bbd96e
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1149733eec3e645a88cec88e3d630409b2fd607fe44382620dcd32de8875ec30
+oid sha256:54d1e6d1d17a3e6c3c7df345bd1082771e2c358f99d3de4cfb119dca7de6672c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90bff0e02e91ee65835a68194924a84afe4e4f8f7cdb643caca99db3408d318f
+oid sha256:e90ac1afdbfcceadfd52e2873c9c0b1d6bffc8cd4bf27f3ca71ac8dfeb745e8d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12164579606440072,
+  "epoch": 0.12880143112701253,
   "eval_steps": 500,
-  "global_step": 340,
+  "global_step": 360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -279,14 +279,30 @@
       "loss": 0.4139,
       "num_input_tokens_seen": 230513,
       "step": 340
+    },
+    {
+      "epoch": 0.1252236135957066,
+      "grad_norm": 0.32019296288490295,
+      "learning_rate": 0.00017495527728085867,
+      "loss": 0.4488,
+      "num_input_tokens_seen": 237103,
+      "step": 350
+    },
+    {
+      "epoch": 0.12880143112701253,
+      "grad_norm": 0.42748796939849854,
+      "learning_rate": 0.0001742397137745975,
+      "loss": 0.4059,
+      "num_input_tokens_seen": 242530,
+      "step": 360
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 230513,
+  "num_input_tokens_seen": 242530,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 5183423338235904.0,
+  "total_flos": 5453643231498240.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null