Training in progress, step 860, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd269f9603e3fe38017dedc2c25f29d5956ffac0a0680ff4be53723cc230308
+oid sha256:7f753704d109104bb1125acdcf9f12fbef1f885465c235982ef55d3483c6c1ca
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:169e61d06045c7d645f7845cd193774033d2c62e8074bc7f3bcd8b429da9c1ff
+oid sha256:8fbd5a1b2192a61e59afc6b4488ed6f766d9a0afb1feca701f1e7b429578040a
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cebdc5bb99a062fec3bff67f2ffff14c060d2d591a43384bf4d1c5af4cf78ddb
+oid sha256:e9b60b57d0860f7eb0d93725cd9d5ecb3ff80ada40fb4afc24fe2f8b4a881ff8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27f27dc8317758e5054e3267c676ecc55b2a293cbb2708d11be857eb327f7ee
+oid sha256:b97d83983c29fc1de97a46291eb4bee37025918a13b0d08e696a566dd59b594e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3005366726296959,
+  "epoch": 0.3076923076923077,
   "eval_steps": 500,
-  "global_step": 840,
+  "global_step": 860,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -679,14 +679,30 @@
       "loss": 0.4159,
       "num_input_tokens_seen": 559943,
       "step": 840
+    },
+    {
+      "epoch": 0.3041144901610018,
+      "grad_norm": 0.2981751263141632,
+      "learning_rate": 0.00013917710196779964,
+      "loss": 0.4099,
+      "num_input_tokens_seen": 566038,
+      "step": 850
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.42181873321533203,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.4365,
+      "num_input_tokens_seen": 574126,
+      "step": 860
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 559943,
+  "num_input_tokens_seen": 574126,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.2591140691769344e+16,
+  "total_flos": 1.2910066276036608e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null