Training in progress, step 72, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a3345b3cfb695d6e86813643d68e1ad6401720719678dea1bd27547d849823
+oid sha256:9167fa5a061c46756d74fb55ce7cc9dfca1d2c9a9820ee119fda30d9ef7656df
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdc795a209011b09ae72dd1646b1b02be9c1f4bbf560af075cbd4352f4e2158
+oid sha256:cbdac76b8a0b0e0d7d4f158b8cf64cabf36c3375f09a6dd0f6ecf72a0d3b79d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08030592734225621,
+  "epoch": 0.09177820267686425,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 14.477,
       "eval_steps_per_second": 1.819,
       "step": 63
+    },
+    {
+      "epoch": 0.0841300191204589,
+      "grad_norm": NaN,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.08795411089866156,
+      "grad_norm": NaN,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.09177820267686425,
+      "grad_norm": NaN,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.09177820267686425,
+      "eval_loss": NaN,
+      "eval_runtime": 91.3258,
+      "eval_samples_per_second": 14.465,
+      "eval_steps_per_second": 1.818,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.488407088182067e+16,
+  "total_flos": 9.696243669899674e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null