Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a94abd88e4ee81674eb7f01a29edd8b19ee8536704ce5a96350eb9f79d3b19
+oid sha256:29fc89425db25a681bf1350715c61e786db812fee3255924a6844327363eb0c7
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0038f9c4cc916603d95a744848cb9dbe6901f5564389c4acdeed724e7671d314
+oid sha256:96905bd7798813512121519ba017906711196030130cc24c687b6674d3ed929f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00024728374263944484,
+  "epoch": 0.0003709256139591673,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 16.808,
       "eval_steps_per_second": 8.404,
       "step": 20
+    },
+    {
+      "epoch": 0.0002596479297714171,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.00029674049116733384,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0003091046782993061,
+      "eval_loss": NaN,
+      "eval_runtime": 2020.9264,
+      "eval_samples_per_second": 16.851,
+      "eval_steps_per_second": 8.426,
+      "step": 25
+    },
+    {
+      "epoch": 0.00033383305256325053,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0003709256139591673,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0003709256139591673,
+      "eval_loss": NaN,
+      "eval_runtime": 2018.034,
+      "eval_samples_per_second": 16.875,
+      "eval_steps_per_second": 8.438,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6921921698463744.0,
+  "total_flos": 1.0630094036926464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null