Training in progress, step 16512, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84490a0ba5e68272e718e1b587f957c02192d8adb3af51f4ee9f3e16c57d8791
+oid sha256:0c52a6dd7e5bc676bd35e2ff08757c004c9a77792d247e5966821ce4cda29d1f
 size 12017472

last-checkpoint/global_step16512/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fecc1fd44558636bf7291a837176c0c5d7117ea5d1c6ded1655d2dd3ac118e40
+size 71982309

last-checkpoint/global_step16512/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b5d77557f0687686c909d8ecd0930cb52e3c8d3394f7825febe171c4601f55
+size 146356645

last-checkpoint/latest

@@ -1 +1 @@
-global_step16500
+global_step16512

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f34d42adfb703043e77cccecb301eb61eb2fb980871ddcbacc2771de139a9c
+oid sha256:9be458c8cf8debad5d6e2a3bd43cb667b3d77295003bd12c52999f7972324e51
 size 14709

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 16000,
   "best_metric": 0.5378558039665222,
   "best_model_checkpoint": "/root/leap-finetune/outputs/sft/lfm2_350m_marathi_optimized_12ep/checkpoint-16000",
-  "epoch": 11.991819669151063,
+  "epoch": 12.0,
   "eval_steps": 250,
-  "global_step": 16500,
+  "global_step": 16512,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6631,12 +6631,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.164882254873231e+17,
+  "total_flos": 9.171257878139372e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null