Training in progress, step 1520, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a023c9a555a15156bd1f3b0eac50642921f8896cc49d86705ca5e46e1a3dea4
+oid sha256:6934f33e0485a5e93f8247584390ac3d2dd6ac5ebc0d900639a9425d88878f24
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20cb133af12395f0079a6433185baec87512b5142bbe45d5c7ead264b147a62b
+oid sha256:1fe44e71b2a9fe40ed1bd72334ea0500055c9c4677f073a92cb4cd9fe7ad1820
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6770c13dffdadbdc7c80304e0bdb979e4d2486cbabf9dbf5458aa9c0e4bdb14e
+oid sha256:fb79755dd2e3cb463f384bad874402b6cb407f2074456dfb434834439195a2f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8319a7acfebd28a7d1b9834780aa2fdd6ff752ee848c5da2e67c4cf03efbd1a9
+oid sha256:61a6a6c4daed47d8d4ed79cb55afe3d49bb782e5d65ae63be3ef22fcec87bb78
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5366726296958855,
+  "epoch": 0.5438282647584973,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 1520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1207,14 +1207,30 @@
       "loss": 0.4016,
       "num_input_tokens_seen": 1007269,
       "step": 1500
+    },
+    {
+      "epoch": 0.5402504472271914,
+      "grad_norm": 0.2978523373603821,
+      "learning_rate": 9.194991055456172e-05,
+      "loss": 0.4019,
+      "num_input_tokens_seen": 1014734,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5438282647584973,
+      "grad_norm": 0.32369324564933777,
+      "learning_rate": 9.123434704830054e-05,
+      "loss": 0.3867,
+      "num_input_tokens_seen": 1022130,
+      "step": 1520
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1007269,
+  "num_input_tokens_seen": 1022130,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.264992274831155e+16,
+  "total_flos": 2.298409415829504e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null