Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39902a9a2cc3980c8322eec02410f89ac9ce9098c7774922eda76b7d600cec41
+oid sha256:126251e49abcd22bc66ab83990b4d084c773db8ef436fb18a0f24b6b0e6a06f9
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad7d01ee99aa7c8ee93a8491d8ed964c00b893b999ae6497baae3f513ac48b0
+oid sha256:e98914f4e09123c424bb01911704f3288ff1495991198d6a4eea70d1830616aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.079250720461095,
+  "epoch": 1.154178674351585,
   "eval_steps": 17,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -537,6 +537,34 @@
       "eval_samples_per_second": 9.567,
       "eval_steps_per_second": 1.208,
       "step": 187
+    },
+    {
+      "epoch": 1.0907780979827089,
+      "grad_norm": NaN,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 1.1080691642651297,
+      "grad_norm": NaN,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 1.1253602305475505,
+      "grad_norm": NaN,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 1.1426512968299711,
+      "grad_norm": NaN,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 0.0,
+      "step": 198
     }
   ],
   "logging_steps": 3,
@@ -551,12 +579,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.380717748322304e+17,
+  "total_flos": 4.6824360568160256e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null