Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc8e53547407bd60e42dbd9d2cf914988611fc5b6cc41e8fa47c98ce49d97046
+oid sha256:566c017e41da4429d06ede53332b2c3c3119d718947d13829bb8dfa442b1324c
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d01ca0b82979c6de3a1d2f7803106932be7dfd22ee2d87b8cad4231c38971aec
+oid sha256:81e3a8bd188cf8aa6bf53014bd8ce627caf1980716220c89d5733178377461a8
 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": 1.0856313497822931,
+  "epoch": 1.1611030478955007,
   "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": 7.077,
       "eval_steps_per_second": 0.903,
       "step": 187
+    },
+    {
+      "epoch": 1.097242380261248,
+      "grad_norm": NaN,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 1.1146589259796806,
+      "grad_norm": NaN,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": NaN,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 1.1494920174165457,
+      "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": 5.3524561305953894e+17,
+  "total_flos": 5.72467641650774e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null