Training in progress, step 250, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b632180e937ab1fa5d61d48b8652b6eb3d9d4cef91094e5cc90d3cee65676b3
+oid sha256:c2f3a2dce7ac8feb25086ea851f461e19f985b0bb61616cd8cf0f4f9ebdbcc49
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0074a94e7be8f39393e7be3ece5718fa75893cad9596eb6bcf3dfb395e3ed98a
+oid sha256:59a10ee867190f2c182bb1a6570b7305c847c3e86c4a7fd1daca0f9423744f3b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007977376329562722,
+  "epoch": 0.010552085092014182,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 11.692,
       "eval_steps_per_second": 5.846,
       "step": 189
+    },
+    {
+      "epoch": 0.008019584669930779,
+      "grad_norm": NaN,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.008441668073611346,
+      "grad_norm": NaN,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 0.5067,
+      "step": 200
+    },
+    {
+      "epoch": 0.008863751477291912,
+      "grad_norm": NaN,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.00928583488097248,
+      "grad_norm": NaN,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.009707918284653047,
+      "grad_norm": NaN,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.010130001688333615,
+      "grad_norm": NaN,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.010552085092014182,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.13841809915904e+17,
+  "total_flos": 1.509693130801152e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null