Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abf52263c1f69836048f5ca022b910b7466001c76b143e7be0c7f2c8865540a9
+oid sha256:4da4ba0b3b0a0060abe31bc5c6fead762f82d90149cf6eecd0b4216b50b9ca27
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cd6212ea449919b16c27f03f3bc6259bca70d0644963554b54b0854f760edf
+oid sha256:3ebefa66f685e689769adaafd457264ae6777a954ae0a77f34d7684be2682c30
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0035485191756516993,
+  "epoch": 0.007097038351303399,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 61.956,
       "eval_steps_per_second": 30.998,
       "step": 13
+    },
+    {
+      "epoch": 0.005459260270233383,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.007097038351303399,
+      "eval_loss": NaN,
+      "eval_runtime": 24.864,
+      "eval_samples_per_second": 62.057,
+      "eval_steps_per_second": 31.049,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 517492942307328.0,
+  "total_flos": 1034985884614656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null