Training in progress, step 1620, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c40a931b938474e7ac0cc0462f5e739d4df2654285098b7df79361b9728b0d3
+oid sha256:a048f86601ba971f672b82718f94bad132e5b83ef0518c001ab7d8b04f8761c4
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d2bcdca872e1be0270e9898679d1483ea5519929122322feaecb3773f192304
+oid sha256:ade7968eeaa11d7a71f3ef59ccd75f826f2bc6dee5950963249d4f00175a0086
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe05823d9b3a4ae96331974951fec2a9554e92db181f365ab8b362c7e4f414f1
+oid sha256:7229499a03050ced172a76d8d9d236be1759d890b794401cb65a0ba41ba1aaf3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cae89a374497dc38b12678021ff8e8e13ee9363e1283e11bc6d982bc4b24c9f
+oid sha256:093216f4a2f15aa62a41addc634f987432a9234bc35332dcb2fa9dd6e471f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5724508050089445,
+  "epoch": 0.5796064400715564,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1287,14 +1287,30 @@
       "loss": 0.4068,
       "num_input_tokens_seen": 1072956,
       "step": 1600
+    },
+    {
+      "epoch": 0.5760286225402504,
+      "grad_norm": 0.4220598042011261,
+      "learning_rate": 8.479427549194992e-05,
+      "loss": 0.4272,
+      "num_input_tokens_seen": 1079895,
+      "step": 1610
+    },
+    {
+      "epoch": 0.5796064400715564,
+      "grad_norm": 0.2898394763469696,
+      "learning_rate": 8.407871198568873e-05,
+      "loss": 0.4022,
+      "num_input_tokens_seen": 1087604,
+      "step": 1620
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1072956,
+  "num_input_tokens_seen": 1087604,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.412699141176525e+16,
+  "total_flos": 2.445637320393523e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null