Training in progress, step 3560, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eaaf1a4b9929034d74b8c50d19a6d8d53c2d26a4f6d02da1080dda4df0a360
+oid sha256:a279bb382c19f7087584582ba555522cb002ccf80a44bbe5e3c597b684301c82
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d9e80974a7703d029c54544f000cb77fd2fc62ef17eaadf206357849796c63
+oid sha256:d8775de7669719bfc6cda900db4b80facb296a4bc38c35ee1dd063ca4e74c637
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcf5824f0c632f86069df2e9f17325eeacf000d5c2583772ef40a9c05221767
+oid sha256:6a23498417c752807362f2bdcefaa146d86c23127f42029519379996e216d6fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09908f90e07d4149404a47b02e836c6f4c444f056f9b8d3bbb5b2be38110c203
+oid sha256:a50c3936e13aaa4712fbbe35f036d9dd60837f2dcabd664a11c642adeb650ebf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2832,
+  "epoch": 0.2848,
   "eval_steps": 500,
-  "global_step": 3540,
+  "global_step": 3560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1246,6 +1246,13 @@
       "learning_rate": 2.833185708216743e-05,
       "loss": 3.53,
       "step": 3540
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 27.148874282836914,
+      "learning_rate": 2.8309521707095835e-05,
+      "loss": 3.4933,
+      "step": 3560
     }
   ],
   "logging_steps": 20,
@@ -1253,7 +1260,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 8383944629747712.0,
+  "total_flos": 8430233772392448.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null