Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af072c31c62cc97f7cfb44e0bfb3e9ecf2a3df48ac2537236ba811eb2177842
+oid sha256:7e479179da053d7aa6b9267888f29a61b871cbd99edfdca282f8d7fe7e2a738b
 size 101107578

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a533315382e7535481b1afbb0f6d8a0f8f9f34b5d2a08249accb3fd9d0bd476
+oid sha256:7d50246edd62d6fd8372215262f8123cdc6dd98273d3e2992feacdcaf9c49fb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005761903732993381,
+  "epoch": 0.0008642855599490072,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.000604999891964305,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006914284479592058,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006914284479592058,
+      "eval_loss": NaN,
+      "eval_runtime": 1629.5334,
+      "eval_samples_per_second": 8.969,
+      "eval_steps_per_second": 4.485,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007778570039541064,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008642855599490072,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1814262460710912.0,
+  "total_flos": 2792162794143744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null