Training in progress, step 750, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ebb21551699498bdfcba38d5f751619afc63fb7fcfa6e47c1d49504a218f1e
+oid sha256:97ea3d1fee0cf94f18c76aded546bd00636402c5d3d8873ce1df5f560490a2ae
 size 265470032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b5f2b8ff300befea10f7d650208277e6d7f19e3a3dc3ec916a46f7b37fff28
+oid sha256:c57f2a2e0d84885a37b25be92d6eb3a16854b88a05cf9befca36265f955848a7
 size 531000890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b3ee0d80a3e664af92a3a2c0f8459861d750756daeb26269af6e98ef5015d1
+oid sha256:950da3e90ce3ce1c506179b66ccc7e74355553896596d9d1885bfe0bd3b8375e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5913199b11707b587684d2f886e94334cc483d491b5cadbc066dd6641919c228
+oid sha256:ab03192a60c4fb6ec6096a859424dfb24171c6b3fc801b38b85ab0fd723b1704
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,14 @@
       "learning_rate": 6.666666666666667e-05,
       "loss": 1.8909,
       "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.6887657642364502,
+      "eval_runtime": 11.4017,
+      "eval_samples_per_second": 87.706,
+      "eval_steps_per_second": 5.526,
+      "step": 500
     }
   ],
   "logging_steps": 500,
@@ -36,12 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 783918600192000.0,
+  "total_flos": 1175877900288000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null