Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6088a98dcda4a0c0aa3cf4c30bf43482faacdaeddc2c6865dee40f331e7196bd
+oid sha256:729f4de7df9f6b922698eafdf20149f85e477d13fdba100b7316aecb5f3e18e2
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64d158d9093e6c962cf31fc3f4a1bbc9a1778eb135d3dcf1d28a7300957aa92
+oid sha256:5184776250d7baf250926e94c1d613f9e5c9c3953dc64f80309a3f355036e05b
 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": 0.0017594018033868484,
+  "epoch": 0.003518803606773697,
   "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": 40.626,
       "eval_steps_per_second": 20.313,
       "step": 10
+    },
+    {
+      "epoch": 0.0021112821640642183,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0026391027050802728,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026391027050802728,
+      "eval_loss": NaN,
+      "eval_runtime": 59.0827,
+      "eval_samples_per_second": 40.519,
+      "eval_steps_per_second": 20.26,
+      "step": 15
+    },
+    {
+      "epoch": 0.0031669232460963272,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.003518803606773697,
+      "eval_loss": NaN,
+      "eval_runtime": 59.1343,
+      "eval_samples_per_second": 40.484,
+      "eval_steps_per_second": 20.242,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 800588279316480.0,
+  "total_flos": 1601176558632960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null