Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e1a7f1302ef5433741a3ee69a87b4b4e833bfd4fd9c9a254b9140e53e23766
+oid sha256:f8b758f8e183471747d3d3f52b864b20d882a9aa0bca9a7b221862cac7093cd2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d9926d3f133af82ae7e4a4ccbc0aea9433213d10d4c711532077bc5fa16be8
+oid sha256:03fa0cc049fd3fab193777840d0153a64719ec79e7f70c56f011e64169f1d1fd
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30dc60382167de3458c5c0efd3fe3f40ca4cde794d0fe66663ca9a8bcee0d065
+oid sha256:bc617f0a2f1b846390f426514e6959c82d9ccca5a06fae71b1179457baa9dd5f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9e707c93d930eada5d65eeb12d5abae9fff751224d824839cf7f999a563f5e
+oid sha256:346a20d6aa585567535ead6c7378b42808548809d68f384868746403a054dab0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5195344970906068,
+  "epoch": 0.6234413965087282,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42,6 +42,13 @@
       "learning_rate": 1.6540592962039347e-05,
       "loss": 0.4387,
       "step": 2500
+    },
+    {
+      "epoch": 0.6234413965087282,
+      "grad_norm": 0.8339985013008118,
+      "learning_rate": 1.584788029925187e-05,
+      "loss": 0.4192,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -61,7 +68,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3044789452800000.0,
+  "total_flos": 3653747343360000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null