Training in progress, step 1140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93756c662435c89f0b33aea427588c404b58d5be37cf76c3f9e4bc0ff1bd939a
+oid sha256:9ccf5782593e66412849cf0331f694759fa6cadfe866582a92dc1f5db7cfb19c
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88dc8585ef97f13c62f73031c2660812fe3125beba7cb9ca7b650ca2dd9be0e
+oid sha256:33ace10175162fbb0251f3a59624654383e563ccfa7daaa8f8a330925f01cfae
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10612cfe26142bef77beb908186e256524851aa5a76ff5646d1e0e1c8e9ff68c
+oid sha256:db963a2a49fb5002a715398d59757b5b39bdbc3ac8e778ee4bf9108f72ec61a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827f3733c0f4c8564e6bc69cab6741789e52e80ec29e9f5a0f4d2f148dfac06d
+oid sha256:76c7c7c62106d50e468f60a02081ed9ee14be8c90f56cb0a1ed1c7569018541d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4007155635062612,
+  "epoch": 0.407871198568873,
   "eval_steps": 500,
-  "global_step": 1120,
+  "global_step": 1140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -903,14 +903,30 @@
       "loss": 0.4179,
       "num_input_tokens_seen": 753315,
       "step": 1120
+    },
+    {
+      "epoch": 0.40429338103756707,
+      "grad_norm": 0.42388609051704407,
+      "learning_rate": 0.00011914132379248659,
+      "loss": 0.3882,
+      "num_input_tokens_seen": 759832,
+      "step": 1130
+    },
+    {
+      "epoch": 0.407871198568873,
+      "grad_norm": 0.3108317255973816,
+      "learning_rate": 0.00011842576028622541,
+      "loss": 0.4247,
+      "num_input_tokens_seen": 766054,
+      "step": 1140
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 753315,
+  "num_input_tokens_seen": 766054,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.693939409943552e+16,
+  "total_flos": 1.7225849223032832e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null