Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2bf4324299976495589aeb5f5a3711b8645627c36ce72ca82912057259d7ce5
+oid sha256:b7a348479a592119a63b9134dab4168df4534843c38621dd7607e4a08d4873e2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b7d0fa8eb8287d4a55dd8123162638f98117302b8fa32bdee7930327042f097
+oid sha256:81c8be9b0017dc13b4234f1a19837781eb4a3a9e02dcab562e8b3c6a2c21834f
 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": 0.016095715856962737,
+  "epoch": 0.021460954475950318,
   "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": 35.677,
       "eval_steps_per_second": 17.838,
       "step": 150
+    },
+    {
+      "epoch": 0.017168763580760256,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.01824181130455777,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.019314859028355287,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.020387906752152803,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.021460954475950318,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.021460954475950318,
+      "eval_loss": NaN,
+      "eval_runtime": 110.1378,
+      "eval_samples_per_second": 35.628,
+      "eval_steps_per_second": 17.814,
+      "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": 2.44312386306048e+16,
+  "total_flos": 3.25749848408064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null