Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196b9b5d3c179d85e244a7ef7be2c742ba4d86fd53959727b4c3f74d6d6e8b74
+oid sha256:7e0b88b069c78377a057ee3670eb5eb4d5899cbb41eaf143d610783d936b09a0
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702fb67e694aff536268c4fb46b57fd3f9e18f5ea9f5d38d1b90a5e8e975bb67
+oid sha256:87d381348a459e58ee0e6bcfb524ade0fbd14082775c8a724bbda8d0f94ed717
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0033846674564224064,
+  "epoch": 0.00507700118463361,
   "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": 6.545084971874738e-05,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.0035539008292435267,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.004061600947706888,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.004061600947706888,
+      "eval_loss": NaN,
+      "eval_runtime": 425.8089,
+      "eval_samples_per_second": 5.845,
+      "eval_steps_per_second": 2.924,
+      "step": 24
+    },
+    {
+      "epoch": 0.0045693010661702485,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.00507700118463361,
+      "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": 1.048251595751424e+16,
+  "total_flos": 1.572377393627136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null