Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6bd90112056d7e13e4968611dad457d290c004bf507a5a6a5c0e016dad95f4
+oid sha256:bb7fae141c50fec6109eccb02250d064ba0e919afbb00943513190b67752ec6a
 size 39428606

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40efb74665fb1c6bf0bd368873dc935cbcf5fbdc9374416ba4bd6e6f6584596
+oid sha256:60c5a28ddd033e839295bcad09d7b0b8fafa88abd5728dc2cda6b4b463a3acef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03734827264239029,
+  "epoch": 0.07469654528478058,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 50.637,
       "eval_steps_per_second": 25.543,
       "step": 10
+    },
+    {
+      "epoch": 0.04481792717086835,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.056022408963585436,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.056022408963585436,
+      "eval_loss": NaN,
+      "eval_runtime": 2.307,
+      "eval_samples_per_second": 48.982,
+      "eval_steps_per_second": 24.708,
+      "step": 15
+    },
+    {
+      "epoch": 0.06722689075630252,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.07469654528478058,
+      "eval_loss": NaN,
+      "eval_runtime": 2.2177,
+      "eval_samples_per_second": 50.954,
+      "eval_steps_per_second": 25.703,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 61427185090560.0,
+  "total_flos": 121489321623552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null