Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97060e82af2f2c3e1395a055936d8c6330c2d2f3c28d7365f7909022563368c7
+oid sha256:b53fc53791399c18b20c15e4068c9d59e2890237db1c26f76951287d2a92680c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02ec99a3c46c937edbcf79f11f6b2c3049a2c4d0e024b409aaa9f9143c908a1
+oid sha256:05449fabdd9cf83d97ae94b914cbc5fa88e9aef0b56c6127b77584e0afe52bfc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f7d71d2520220b24b14e74f15b8fc66bb3fd91884b9f80b2d1815e9fc2c23c
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004220834036805673,
+  "epoch": 0.0008441668073611346,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,87 @@
       "eval_samples_per_second": 9.639,
       "eval_steps_per_second": 4.819,
       "step": 20
+    },
+    {
+      "epoch": 0.00044318757386459565,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005065000844166807,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005276042546007091,
+      "eval_loss": NaN,
+      "eval_runtime": 1035.7309,
+      "eval_samples_per_second": 9.632,
+      "eval_steps_per_second": 4.816,
+      "step": 25
+    },
+    {
+      "epoch": 0.0005698125949687658,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.000633125105520851,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.000633125105520851,
+      "eval_loss": NaN,
+      "eval_runtime": 1035.858,
+      "eval_samples_per_second": 9.631,
+      "eval_steps_per_second": 4.815,
+      "step": 30
+    },
+    {
+      "epoch": 0.000696437616072936,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0007386459564409927,
+      "eval_loss": NaN,
+      "eval_runtime": 1035.6853,
+      "eval_samples_per_second": 9.632,
+      "eval_steps_per_second": 4.816,
+      "step": 35
+    },
+    {
+      "epoch": 0.0007597501266250211,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0008230626371771062,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0008441668073611346,
+      "eval_loss": NaN,
+      "eval_runtime": 1035.714,
+      "eval_samples_per_second": 9.632,
+      "eval_steps_per_second": 4.816,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -103,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4358587790917632.0,
+  "total_flos": 9366326954950656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null