Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:103d4a4a107057d19fba9f14c0c6560aa6c7a951a77920fa9b45fa25329a104e
+oid sha256:234c3e98412e14581418b5fd05442cfe7ac082163b446e69632c6327093b1206
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5a21369472f7194a689fd05a0d4917e15d37a7a4183d7b7f6bb86f363a89788
+oid sha256:a17d17b9002e5371c9b9516a2721508ac20c423578bfe307003d10a9accd4609
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03499562554680665,
+  "epoch": 0.04666083406240887,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,43 @@
       "eval_samples_per_second": 30.373,
       "eval_steps_per_second": 15.228,
       "step": 30
+    },
+    {
+      "epoch": 0.03849518810148731,
+      "grad_norm": NaN,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.040828229804607756,
+      "eval_loss": NaN,
+      "eval_runtime": 11.8779,
+      "eval_samples_per_second": 30.392,
+      "eval_steps_per_second": 15.238,
+      "step": 35
+    },
+    {
+      "epoch": 0.04199475065616798,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.045494313210848646,
+      "grad_norm": NaN,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.04666083406240887,
+      "eval_loss": NaN,
+      "eval_runtime": 11.8817,
+      "eval_samples_per_second": 30.383,
+      "eval_steps_per_second": 15.234,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -147,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2401764837949440.0,
+  "total_flos": 3202353117265920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null