Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d45d7b935a229b5dc66e76494a9291085933a04a88e834a628811cc1092e71c
+oid sha256:81599beec9c6113b0b429f082284e9f0045579dcfd3c2f42045a4e058e33aa8a
 size 70674004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f9170e9d99eda010c52e7404c10425366333ff9aa88e8bf3935d52a625f802
+oid sha256:4ab9c76a295686ba2305b1beb5d9ede2fc99aff7eb2befed54a2695d4c194452
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4105263157894737,
+  "epoch": 0.5263157894736842,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.0,
       "step": 35
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": NaN,
+      "eval_runtime": 4.6374,
+      "eval_samples_per_second": 8.841,
+      "eval_steps_per_second": 4.528,
+      "step": 40
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": NaN,
+      "eval_runtime": 4.6683,
+      "eval_samples_per_second": 8.783,
+      "eval_steps_per_second": 4.498,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.3443293748658176e+16,
+  "total_flos": 1.72349919854592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null