Training in progress, step 72, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebca97e9fd3ccc847bc041f65eaf2dd5ef3ef75a755dbc12a481d1e23e63943b
+oid sha256:f6b9b8306db003392118c4a7e814e2f12b62b113376c4fab3d8a4915b814fd83
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63eb6e69f6f7d9904bc94aeeed5d2d905f7e153a3f6407edf275ba5537bef7d9
+oid sha256:40a43ec492e5785b0e7fbad5c56247559494a613c2df8a4ccd52827cfec5f278
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
+oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08231595279898739,
+  "epoch": 0.09407537462741415,
   "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": 4.034,
       "eval_steps_per_second": 2.017,
       "step": 63
+    },
+    {
+      "epoch": 0.08623576007512963,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.09015556735127189,
+      "grad_norm": NaN,
+      "learning_rate": 6.538829429225069e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.09407537462741415,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.09407537462741415,
+      "eval_loss": NaN,
+      "eval_runtime": 927.4346,
+      "eval_samples_per_second": 2.78,
+      "eval_steps_per_second": 1.39,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.443867598697267e+17,
+  "total_flos": 7.364420112796877e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null