Training in progress, step 2836, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c76f349cf7916b8a526a00272e9e9774693824420168081f1d0d14d27ec477
+oid sha256:75763f7d3626516994b31f37f9c71b89fe1c4931e31a81dce9ec75e7444f222f
 size 557912620

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819d88698704f79e890c488b84907a8531f4eec5200d16b4066829b7b5b359bb
+oid sha256:531b511d4e83008119f801defafb040e8cec0ca7220192f17d6491a3727b6dd7
 size 1115579834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a44a7d01e7a1e697bee1e2fac088fa92d9b6d757f620da1c95ab22db79f4ff3d
+oid sha256:bffa0c819d4bb9f16a80c0c37a452508456cc1e3725c086d1afb6ca62a842d06
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9ea3d03d222f67be1c1c3ebbcd1c13a13e443e03074a240028e9e3ec52cb98
+oid sha256:b55747937ecf5eb52214b61898d359fcd6713947b12fe4e4bb1c3f1d9bb05147
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7052186177715092,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2836,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,27 @@
       "learning_rate": 1.4756699576868829e-05,
       "loss": 0.0009,
       "step": 2000
+    },
+    {
+      "epoch": 0.7933709449929478,
+      "grad_norm": 0.10926026105880737,
+      "learning_rate": 1.0349083215796897e-05,
+      "loss": 0.0004,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8815232722143864,
+      "grad_norm": 0.5444942712783813,
+      "learning_rate": 5.9414668547249645e-06,
+      "loss": 0.0005,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9696755994358252,
+      "grad_norm": 0.10924108326435089,
+      "learning_rate": 1.5338504936530325e-06,
+      "loss": 0.0004,
+      "step": 2750
     }
   ],
   "logging_steps": 250,
@@ -78,12 +99,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4877891665920000.0,
+  "total_flos": 6914716304670720.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null