Training in progress, step 380, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc49fc34045419f2a9dace17402a22103368094c6a2987a1616d0e939d14e164
+oid sha256:bdcdc0f35846bc754577cd10e20f7cd208a8c3b9782dd1734562927f12aa9ff4
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a88e35eeb6b5fa8d07251e65fe421367b7e6e5c40b58ad1d552622a1bbd96e
+oid sha256:c222ad7729e8edc625af49bfa2accf203ab4ff265dd02ca19ee4431b28a163f1
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54d1e6d1d17a3e6c3c7df345bd1082771e2c358f99d3de4cfb119dca7de6672c
+oid sha256:670f2e3ed201a39b7134ca5f6503aca666cb99ac973528bcdb06393401ddc686
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e90ac1afdbfcceadfd52e2873c9c0b1d6bffc8cd4bf27f3ca71ac8dfeb745e8d
+oid sha256:a770cb4ae613cc009292941b2afefaa83fcb03984ba92a4fe9b157b556d9e215
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12880143112701253,
+  "epoch": 0.13595706618962433,
   "eval_steps": 500,
-  "global_step": 360,
+  "global_step": 380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -295,14 +295,30 @@
       "loss": 0.4059,
       "num_input_tokens_seen": 242530,
       "step": 360
+    },
+    {
+      "epoch": 0.13237924865831843,
+      "grad_norm": 0.39997342228889465,
+      "learning_rate": 0.00017352415026833634,
+      "loss": 0.4069,
+      "num_input_tokens_seen": 247524,
+      "step": 370
+    },
+    {
+      "epoch": 0.13595706618962433,
+      "grad_norm": 0.45402902364730835,
+      "learning_rate": 0.00017280858676207514,
+      "loss": 0.4354,
+      "num_input_tokens_seen": 252526,
+      "step": 380
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 242530,
+  "num_input_tokens_seen": 252526,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 5453643231498240.0,
+  "total_flos": 5678417971703808.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null