Training in progress, step 27, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31dde8579a0157dbc47a9b5157de18564af0aad9b898db302c80bc1ecc7e01e0
+oid sha256:c631f23bb5860cf4eef17638b11e53ba36660a462ffc2bd582233024b2983071
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa9423a907785e1975e1cacdbbc1addd40ea1e7958d6da6deb0c44d64a8b8946
+oid sha256:f1be5635e7fe5aed02620b4be3bcb48bec5ddb23cc4a2d0ee067ac7be2b6d243
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b679dfcad285902b67d18379c2cc1ca0aebfc7646cb33fa82a3fb8ed15c820
+oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020178665265370467,
+  "epoch": 0.0302679978980557,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 8.267,
       "eval_steps_per_second": 4.135,
       "step": 18
+    },
+    {
+      "epoch": 0.02354177614293221,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014994217771805422,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.026904887020493956,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014907662554463532,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0302679978980557,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001471841427340235,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0302679978980557,
+      "eval_loss": NaN,
+      "eval_runtime": 363.5241,
+      "eval_samples_per_second": 8.266,
+      "eval_steps_per_second": 4.135,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1488560963334963e+17,
+  "total_flos": 1.732609275152302e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null