Training in progress, step 2320, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f78f8e128e75e11b3bd24fe3cafa27eb00c4b149658842b4a45b224ec5f5ee22
+oid sha256:ff6279bb72a1a41fb48956b4feb1a93393d18d4e6392ad78211fc04c9f099df2
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b815a874278b1223221c3e50dc80f1ff0a4372ec10c87401ec27f3ea0c36a67a
+oid sha256:74ccf80491212ab3533b791bb0a94ac69d6d47751d6deeebce7061fdefd9b30f
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502b3acd424d63dc379a6747cfdc8fa58c6c30b6487e9ba722dee624541749e4
+oid sha256:19bb1874a3bf4e8cd76c40201bfecc47f7333e535e927638bb37015a23fd28aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc458452416b9e8ad2bf3686e504ce90d7aec8e9da53788a9e1ab68961ab5745
+oid sha256:830ffa36a2cc85b79b79c8f68dead7aaec7fb58f5ebad1169970ef47fdf22b5f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8228980322003577,
+  "epoch": 0.8300536672629696,
   "eval_steps": 500,
-  "global_step": 2300,
+  "global_step": 2320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1847,14 +1847,30 @@
       "loss": 0.395,
       "num_input_tokens_seen": 1559137,
       "step": 2300
+    },
+    {
+      "epoch": 0.8264758497316637,
+      "grad_norm": 0.25360018014907837,
+      "learning_rate": 3.4704830053667264e-05,
+      "loss": 0.3743,
+      "num_input_tokens_seen": 1565661,
+      "step": 2310
+    },
+    {
+      "epoch": 0.8300536672629696,
+      "grad_norm": 0.27616095542907715,
+      "learning_rate": 3.3989266547406084e-05,
+      "loss": 0.3971,
+      "num_input_tokens_seen": 1572070,
+      "step": 2320
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1559137,
+  "num_input_tokens_seen": 1572070,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.5059485206071296e+16,
+  "total_flos": 3.535030270457856e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null