Training in progress, step 3580, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a279bb382c19f7087584582ba555522cb002ccf80a44bbe5e3c597b684301c82
+oid sha256:8973c002011f7f1b9898a29aed0c9bab5843eb09cdda6107a4a5cced83da0ae1
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8775de7669719bfc6cda900db4b80facb296a4bc38c35ee1dd063ca4e74c637
+oid sha256:5f7f81d4d1f3bbb4230cc8c8dc308cda42affb803c02645e414ec74a4c1f265e
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a23498417c752807362f2bdcefaa146d86c23127f42029519379996e216d6fc
+oid sha256:da4d99ffa87904e6b79db14e0ce4002f8d75f4ea2e6431aa6caa66c2cc565031
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50c3936e13aaa4712fbbe35f036d9dd60837f2dcabd664a11c642adeb650ebf
+oid sha256:ebd0c8b6de9b2d27d16b51d811c091dfd903215da9d823fb4789b5397d7f1dd1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2848,
+  "epoch": 0.2864,
   "eval_steps": 500,
-  "global_step": 3560,
+  "global_step": 3580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1253,6 +1253,13 @@
       "learning_rate": 2.8309521707095835e-05,
       "loss": 3.4933,
       "step": 3560
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 28.534822463989258,
+      "learning_rate": 2.8287046721439487e-05,
+      "loss": 3.5881,
+      "step": 3580
     }
   ],
   "logging_steps": 20,
@@ -1260,7 +1267,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8430233772392448.0,
+  "total_flos": 8475145066708992.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null