Training in progress, step 1650, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1128faf5e4f88e09f035caa83996e406d072d8727ad0f66f62a5acb34604ae9
+oid sha256:270eea5abc85b30c5b391ee943200b572ee6369f4bdcf1baf2ea7257ec5ee51a
 size 516567560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ea2143d213566e75a8dee50e22b9bad965083cb2af7968e50389d7f34152b1
+oid sha256:ffad7d3de12e2fddbb9835651d0e1268205875bf3c3d51aa6abe70df83c6268f
 size 1033289547

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4e2d2649c871f0f92d612c20c48748bb85a6235bdb14748f5eb6eb22a94f0f
+oid sha256:b87c9b5dbfbe5f2edd77d557ec08621b8fbc8489a95b736859b5639a0921c1bf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03936911001205679,
+  "epoch": 0.040599394699933566,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,13 @@
       "learning_rate": 4.9891791269792073e-05,
       "loss": 0.0697,
       "step": 1600
+    },
+    {
+      "epoch": 0.040599394699933566,
+      "grad_norm": 0.6289940476417542,
+      "learning_rate": 4.988253022856661e-05,
+      "loss": 0.0729,
+      "step": 1650
     }
   ],
   "logging_steps": 50,
@@ -251,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 769805801994240.0,
+  "total_flos": 792849378816000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null