Training in progress, step 2880, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f42cba240aace3a7aa0f5f7c273be1525eb8be352f43f1cf0bdb166bd389200
+oid sha256:ec579228de33375bef3c021708802215d4a04652827a6f8c051e98faa86a4a30
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52dcfe82a17e2f1eb54dae75c8dbe54ec769ced09ea24be0872bea36653a23a8
+oid sha256:3882deb1f77706d02be4f5b35744aae6ff1859c7fa25beb0cc12f83b8c1d253b
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e48ee25396e10f035ab07c8ed024ed74a68f3a713cfc75199db428d17dd71b
+oid sha256:8c86d865b5f454c32bd8b51f5d37d59633a8c46276d5fa7f3794da39892d4027
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c72934a4b9c9f30c92be2812c4cdd34569fcf3bc14ed03c2c556b5f34f3c8a
+oid sha256:51ced696ae0a3d60fb2ccce1b7a31e63100064311d81188f38315caced36b56c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2288,
+  "epoch": 0.2304,
   "eval_steps": 500,
-  "global_step": 2860,
+  "global_step": 2880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1008,6 +1008,13 @@
       "learning_rate": 2.900660602239667e-05,
       "loss": 3.498,
       "step": 2860
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 28.681190490722656,
+      "learning_rate": 2.8989147084546335e-05,
+      "loss": 3.501,
+      "step": 2880
     }
   ],
   "logging_steps": 20,
@@ -1015,7 +1022,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 6767138034352128.0,
+  "total_flos": 6812114940493824.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null