Training in progress, step 24, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b590db5b2a28d85c0b82d5580062e98db2d95e7e75fafdcf726fbbacea9f32be
+oid sha256:c9c1d6bdd755319f1f434c95c22ec7ff65d2136a02928e38d507f58dc50ed300
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1220a35005eeb73eee58f3c7ed357c175737e6d8476f3d618898c86e0d179e11
+oid sha256:af7e627a0f75e8e1695b923aa7f2e71fc850c47eaa8c8adc15535761677b7864
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
+oid sha256:470670603e8fdc5330cdb9a9152c4fd9c3d8c5a74dd26bffbbb0d869d097eafa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021691973969631236,
+  "epoch": 0.026030368763557483,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,42 @@
       "eval_samples_per_second": 7.652,
       "eval_steps_per_second": 3.836,
       "step": 20
+    },
+    {
+      "epoch": 0.0227765726681128,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.02386117136659436,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.024945770065075923,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.026030368763557483,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.026030368763557483,
+      "eval_loss": NaN,
+      "eval_runtime": 50.847,
+      "eval_samples_per_second": 7.65,
+      "eval_steps_per_second": 3.835,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -214,7 +250,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5589685858467840.0,
+  "total_flos": 6707623030161408.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null