Training in progress, step 450, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ab5813665187b9d25ec285cc585f3d0d40af665ead384265ff6798890b234a
+oid sha256:459566b93d2ca5773d38915ead0b303b0c27edb9d2386a5b34aff5c60a377d5b
 size 298031674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:880c0387a39df6cd851f00814a1e3935116dccddb1f54103179213e3cd5747de
+oid sha256:4f19d4ea7ef0565d094ffa0dd00dccb28b33a4ac5569fd9a6c891ab0cd1252f3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1acbada17dd14707c522d6bfe6682855790daf7760c7d8cce7a5b80f4e4bf50
+oid sha256:10b6a107d5f9c6404fe4457c524bcd67ebd6df39097f11f68fe1ba4b442f88d6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": Infinity,
   "best_model_checkpoint": null,
-  "epoch": 0.017591180954614753,
+  "epoch": 0.02638677143192213,
   "eval_steps": 150,
-  "global_step": 300,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -233,6 +233,119 @@
       "eval_samples_per_second": 34.247,
       "eval_steps_per_second": 34.247,
       "step": 300
+    },
+    {
+      "epoch": 0.018177553653101912,
+      "grad_norm": NaN,
+      "learning_rate": 4.977374404419837e-05,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.01876392635158907,
+      "grad_norm": NaN,
+      "learning_rate": 4.975171939123005e-05,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.01935029905007623,
+      "grad_norm": NaN,
+      "learning_rate": 4.9728677292023405e-05,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.019936671748563388,
+      "grad_norm": NaN,
+      "learning_rate": 4.970461869374889e-05,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.020523044447050547,
+      "grad_norm": NaN,
+      "learning_rate": 4.967954458536126e-05,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.021109417145537705,
+      "grad_norm": NaN,
+      "learning_rate": 4.965345599755887e-05,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.021695789844024864,
+      "grad_norm": NaN,
+      "learning_rate": 4.962635400274142e-05,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.02228216254251202,
+      "grad_norm": NaN,
+      "learning_rate": 4.959823971496574e-05,
+      "loss": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.022868535240999178,
+      "grad_norm": NaN,
+      "learning_rate": 4.95691142899001e-05,
+      "loss": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.023454907939486336,
+      "grad_norm": NaN,
+      "learning_rate": 4.9538978924776634e-05,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.024041280637973495,
+      "grad_norm": NaN,
+      "learning_rate": 4.9507834858342186e-05,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.024627653336460654,
+      "grad_norm": NaN,
+      "learning_rate": 4.9475683370807326e-05,
+      "loss": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.025214026034947812,
+      "grad_norm": NaN,
+      "learning_rate": 4.9442525783793794e-05,
+      "loss": 0.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.02580039873343497,
+      "grad_norm": NaN,
+      "learning_rate": 4.940836346028011e-05,
+      "loss": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.02638677143192213,
+      "grad_norm": NaN,
+      "learning_rate": 4.937319780454559e-05,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.02638677143192213,
+      "eval_loss": NaN,
+      "eval_runtime": 14.5365,
+      "eval_samples_per_second": 34.396,
+      "eval_steps_per_second": 34.396,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -247,12 +360,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.1471056870805504e+16,
+  "total_flos": 3.2262259381248e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null