Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654b23694cdd1bbec4f90862155f3f41c2a6bcac9229cb226a66d80cc205f4cc
+oid sha256:1a6d51afb5613c7e07b57dba34d6e18086edbcf93686c18e65caf50ce10b821e
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2fdce7da28ed66b3d91cfa2a1cbe53544b2858c9aa4b494826630ef96e4b87c
+oid sha256:0c78f94cf2f5d394f6ffbcbada32faaf7421d6e7e2210fc0b7aa3f9304f69fb1
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d27a260316eae40f12eb26cf979926c13542623ae9f28e7854a86a259b8f86ac
+oid sha256:e56e2dd61d2120005a26d903703b6fbaef4472282e0e02d16683e4bcff04ca50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6154d037b631b5f05d1997c63d1a8dc99cf7eb96d3d6cf27edbd3ad94f018941
+oid sha256:8bfb1808e171f97eba17f5beca7d0a41ebaaf65e4eb012e17bca2fb8e72cb499
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2224,
+  "epoch": 0.224,
   "eval_steps": 500,
-  "global_step": 2780,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -980,6 +980,13 @@
       "learning_rate": 2.9074970738873054e-05,
       "loss": 3.6409,
       "step": 2780
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 27.53672218322754,
+      "learning_rate": 2.9058100575095156e-05,
+      "loss": 3.5903,
+      "step": 2800
     }
   ],
   "logging_steps": 20,
@@ -987,7 +994,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6577585471488000.0,
+  "total_flos": 6625810162974720.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null