Training in progress, step 1540, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6934f33e0485a5e93f8247584390ac3d2dd6ac5ebc0d900639a9425d88878f24
+oid sha256:7b3ff122300a18d57c853e25e590e16786c7ad419f48524c7cbf11ccb071c190
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe44e71b2a9fe40ed1bd72334ea0500055c9c4677f073a92cb4cd9fe7ad1820
+oid sha256:636171340db7557397e62ad8d25bdf32a718d2d9d58de677060e6a51a635f297
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb79755dd2e3cb463f384bad874402b6cb407f2074456dfb434834439195a2f8
+oid sha256:d7156da34db6a913e161eace9419c4bd917f16d306983c0686b60a669b6fb753
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a6a6c4daed47d8d4ed79cb55afe3d49bb782e5d65ae63be3ef22fcec87bb78
+oid sha256:ea3157897b0fd7796a4bb8ecade679914447a9babe2f9fec4f85adecca7e3f9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5438282647584973,
+  "epoch": 0.5509838998211091,
   "eval_steps": 500,
-  "global_step": 1520,
+  "global_step": 1540,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1223,14 +1223,30 @@
       "loss": 0.3867,
       "num_input_tokens_seen": 1022130,
       "step": 1520
+    },
+    {
+      "epoch": 0.5474060822898033,
+      "grad_norm": 0.34458237886428833,
+      "learning_rate": 9.051878354203936e-05,
+      "loss": 0.4247,
+      "num_input_tokens_seen": 1029090,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5509838998211091,
+      "grad_norm": 0.34909483790397644,
+      "learning_rate": 8.980322003577818e-05,
+      "loss": 0.4164,
+      "num_input_tokens_seen": 1035252,
+      "step": 1540
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1022130,
+  "num_input_tokens_seen": 1035252,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.298409415829504e+16,
+  "total_flos": 2.3279161599369216e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null