Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9cfc8ccd959cc28b94fe4e9b5271f98586d2c2bec8a3ae3a191b499690dcefd
+oid sha256:a25356f1d4da875880fb13346a4087d097ad469aced44a354bf5582f0c250ed7
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72db1ca300703148b11f6c9ce555ec1a4f9c50722bf07f81b60e9a09bb963e32
+oid sha256:0fa35b6de9fbecad86e774e77fb033c4f30e424d941140304ce3af50ca82c67d
 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": 0.003623356714823245,
+  "epoch": 0.004645329121568263,
   "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": 0.0037162632972546103,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0037162632972546103,
+      "eval_loss": NaN,
+      "eval_runtime": 155.5516,
+      "eval_samples_per_second": 29.135,
+      "eval_steps_per_second": 14.568,
+      "step": 40
+    },
+    {
+      "epoch": 0.004180796209411437,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.004645329121568263,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.004645329121568263,
+      "eval_loss": NaN,
+      "eval_runtime": 155.2697,
+      "eval_samples_per_second": 29.188,
+      "eval_steps_per_second": 14.594,
+      "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": 1313407946981376.0,
+  "total_flos": 1686350944272384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null