Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681b9a3c017f51d23d63cfa771b07651de0ea6f520809cdfb0f7484a51dd5777
+oid sha256:3edebdfad9ee1fb8b8daf8ef97b4e60cba0f86572c1d59206cf6329806df257c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3202c18da649b1f0e77c873cd6f028f8e87862db021d3d223b235a7e44b92729
+oid sha256:d4cc23a70bfc0619c9ae7ca17c381651d9920f3ca604026b002f92c81ee2d35e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01722949689869056,
+  "epoch": 0.02297266253158741,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 18.574,
       "eval_steps_per_second": 9.292,
       "step": 150
+    },
+    {
+      "epoch": 0.018378130025269928,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.2116,
+      "step": 160
+    },
+    {
+      "epoch": 0.0195267631518493,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.1141,
+      "step": 170
+    },
+    {
+      "epoch": 0.02067539627842867,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.02182402940500804,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0809,
+      "step": 190
+    },
+    {
+      "epoch": 0.02297266253158741,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0745,
+      "step": 200
+    },
+    {
+      "epoch": 0.02297266253158741,
+      "eval_loss": NaN,
+      "eval_runtime": 98.6665,
+      "eval_samples_per_second": 18.578,
+      "eval_steps_per_second": 9.294,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.592790026387456e+16,
+  "total_flos": 3.440939984171827e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null