Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e11f24ecffda164f06cdd9dacb4290900efeb52400fe498b008397704b1e153
+oid sha256:4c0902123b7ce12f682124ca9b7659ceace9da91e87b23f67c825372f2e81c97
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2686563472cd649084082a2c329fd627ce86023a87d1ac3f5dd126e100dfda
+oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007838526357044876,
+  "epoch": 0.0011757789535567313,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.976,
       "eval_steps_per_second": 2.988,
       "step": 20
+    },
+    {
+      "epoch": 0.0008230452674897119,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009406231628453851,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009798157946306093,
+      "eval_loss": NaN,
+      "eval_runtime": 1798.0158,
+      "eval_samples_per_second": 5.975,
+      "eval_steps_per_second": 2.988,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010582010582010583,
+      "grad_norm": NaN,
+      "learning_rate": 7.920883091822408e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011757789535567313,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0011757789535567313,
+      "eval_loss": NaN,
+      "eval_runtime": 1798.0739,
+      "eval_samples_per_second": 5.975,
+      "eval_steps_per_second": 2.988,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -108,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7031294986813440.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null