Training in progress, step 500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c936e33e771d64f59c0320ef76f702c8baefb76b8a6061a149f15476d3954e7a
+oid sha256:2b5cc02df0978144eae867d60ee9993ebc71b311738246cc4124079c1ab1194a
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902a971a6dd3166551a11be2e45b39a3a9ecf36ab45d22f6eb5fc1988a7caf24
+oid sha256:4818fc094295b000819bdff7703a1703fef8b036a45368cd18f1d434ead8d998
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5284529596797255,
+  "epoch": 0.5719187875321704,
   "eval_steps": 42,
-  "global_step": 462,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1181,6 +1181,90 @@
       "eval_samples_per_second": 14.368,
       "eval_steps_per_second": 3.599,
       "step": 462
+    },
+    {
+      "epoch": 0.5318844724049185,
+      "grad_norm": NaN,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 0.0,
+      "step": 465
+    },
+    {
+      "epoch": 0.5353159851301115,
+      "grad_norm": NaN,
+      "learning_rate": 1.0486332583853563e-06,
+      "loss": 0.0,
+      "step": 468
+    },
+    {
+      "epoch": 0.5387474978553045,
+      "grad_norm": NaN,
+      "learning_rate": 8.617714201998084e-07,
+      "loss": 0.0,
+      "step": 471
+    },
+    {
+      "epoch": 0.5421790105804976,
+      "grad_norm": NaN,
+      "learning_rate": 6.93088004882253e-07,
+      "loss": 0.0,
+      "step": 474
+    },
+    {
+      "epoch": 0.5456105233056906,
+      "grad_norm": NaN,
+      "learning_rate": 5.426454159531913e-07,
+      "loss": 0.0,
+      "step": 477
+    },
+    {
+      "epoch": 0.5490420360308836,
+      "grad_norm": NaN,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.5524735487560767,
+      "grad_norm": NaN,
+      "learning_rate": 2.966985702759828e-07,
+      "loss": 0.0,
+      "step": 483
+    },
+    {
+      "epoch": 0.5559050614812696,
+      "grad_norm": NaN,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 0.0,
+      "step": 486
+    },
+    {
+      "epoch": 0.5593365742064627,
+      "grad_norm": NaN,
+      "learning_rate": 1.2429479634897267e-07,
+      "loss": 0.0,
+      "step": 489
+    },
+    {
+      "epoch": 0.5627680869316557,
+      "grad_norm": NaN,
+      "learning_rate": 6.575554083078084e-08,
+      "loss": 0.0,
+      "step": 492
+    },
+    {
+      "epoch": 0.5661995996568487,
+      "grad_norm": NaN,
+      "learning_rate": 2.568918996560532e-08,
+      "loss": 0.0,
+      "step": 495
+    },
+    {
+      "epoch": 0.5696311123820418,
+      "grad_norm": NaN,
+      "learning_rate": 4.110566084036816e-09,
+      "loss": 0.0,
+      "step": 498
     }
   ],
   "logging_steps": 3,
@@ -1195,12 +1279,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.569125726283366e+17,
+  "total_flos": 7.1094434267136e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null