Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84d643f55d070b8de74f1ee9e30e3d17387c215aa6bb4a3e588dc1ad38821fa
+oid sha256:5726d63e4ce8a403eccd56097390137f3ecc226e70bc67d2c7aabc90547b3743
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58b9c4529fccc73f88991d86f843b07b988e6c2b8fda14413d6a5dc5d2f733c
+oid sha256:4c8760177d65af4dda280e8136e6bc81afef274307ad17a1a5d29adc7f7ea52a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1534526854219949,
+  "epoch": 0.1918158567774936,
   "eval_steps": 13,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -130,6 +130,27 @@
       "eval_samples_per_second": 17.593,
       "eval_steps_per_second": 4.405,
       "step": 39
+    },
+    {
+      "epoch": 0.16112531969309463,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.17263427109974425,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.18414322250639387,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
     }
   ],
   "logging_steps": 3,
@@ -144,12 +165,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.5786296085446656e+16,
+  "total_flos": 4.455273774396211e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null