Training in progress, step 462, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f06539a97078f4c0d92767cc0e150d2a513b0f8a07cdfb982a87634c993416d0
+oid sha256:b09a447c660152954dc6252f1fdded02a7979afb0d85a85a4fee85194a30a2a8
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1b52bf45667416d27a79e876f73a7096ab7bec6f0337ef1273ce52b2ceeb8f
+oid sha256:4f7c7a297b02b6fa19e3dd0066ea2aec896bba3774e114d345cddffb534088d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9507fdefdfac1d5dbc7a23a3aeb675b6dd3cc22a3762b7e85ff02a1c9c43105
+oid sha256:7b58b44a2d5024ddc12e64ead45d5d25c7fc985d9aaeb44c7bc3de9b8cf56f23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022322318332203932,
+  "epoch": 0.024554550165424325,
   "eval_steps": 42,
-  "global_step": 420,
+  "global_step": 462,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1075,6 +1075,112 @@
       "eval_samples_per_second": 13.38,
       "eval_steps_per_second": 1.673,
       "step": 420
+    },
+    {
+      "epoch": 0.022481763463148244,
+      "grad_norm": NaN,
+      "learning_rate": 5.9702234071631e-06,
+      "loss": 0.0,
+      "step": 423
+    },
+    {
+      "epoch": 0.02264120859409256,
+      "grad_norm": NaN,
+      "learning_rate": 5.5226705990794155e-06,
+      "loss": 0.0,
+      "step": 426
+    },
+    {
+      "epoch": 0.02280065372503687,
+      "grad_norm": NaN,
+      "learning_rate": 5.091571939329048e-06,
+      "loss": 0.0,
+      "step": 429
+    },
+    {
+      "epoch": 0.022960098855981187,
+      "grad_norm": NaN,
+      "learning_rate": 4.677086910538092e-06,
+      "loss": 0.0,
+      "step": 432
+    },
+    {
+      "epoch": 0.0231195439869255,
+      "grad_norm": NaN,
+      "learning_rate": 4.279368849209381e-06,
+      "loss": 0.0,
+      "step": 435
+    },
+    {
+      "epoch": 0.023278989117869815,
+      "grad_norm": NaN,
+      "learning_rate": 3.898564888996476e-06,
+      "loss": 0.0,
+      "step": 438
+    },
+    {
+      "epoch": 0.023438434248814127,
+      "grad_norm": NaN,
+      "learning_rate": 3.534815906272404e-06,
+      "loss": 0.0,
+      "step": 441
+    },
+    {
+      "epoch": 0.023597879379758442,
+      "grad_norm": NaN,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 0.0,
+      "step": 444
+    },
+    {
+      "epoch": 0.023757324510702754,
+      "grad_norm": NaN,
+      "learning_rate": 2.8590147820153513e-06,
+      "loss": 0.0,
+      "step": 447
+    },
+    {
+      "epoch": 0.02391676964164707,
+      "grad_norm": NaN,
+      "learning_rate": 2.547212649466568e-06,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.024076214772591382,
+      "grad_norm": NaN,
+      "learning_rate": 2.2529654198854835e-06,
+      "loss": 0.0,
+      "step": 453
+    },
+    {
+      "epoch": 0.024235659903535697,
+      "grad_norm": NaN,
+      "learning_rate": 1.9763819484490355e-06,
+      "loss": 0.0,
+      "step": 456
+    },
+    {
+      "epoch": 0.02439510503448001,
+      "grad_norm": NaN,
+      "learning_rate": 1.7175645557220566e-06,
+      "loss": 0.0,
+      "step": 459
+    },
+    {
+      "epoch": 0.024554550165424325,
+      "grad_norm": NaN,
+      "learning_rate": 1.4766089898042678e-06,
+      "loss": 0.0,
+      "step": 462
+    },
+    {
+      "epoch": 0.024554550165424325,
+      "eval_loss": NaN,
+      "eval_runtime": 2367.962,
+      "eval_samples_per_second": 13.382,
+      "eval_steps_per_second": 1.673,
+      "step": 462
     }
   ],
   "logging_steps": 3,
@@ -1094,7 +1200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.433810413351076e+17,
+  "total_flos": 7.090013820105523e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null