Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a87a718681ae26de2607be4cda2d04b6af6b27d591be2c68820c9f934a7c2b0
+oid sha256:5685d41458363868dd6062a44e770be5a7cd162528a7419361b5f9c4b8135aff
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9138bd6a415b1283b8cae260b2d5aa498f2918d4d3ce14de33ccba4ab5193f94
+oid sha256:4b04185bc9c4a212cb29759e873b7839340867473b9f3b1d14465d77a47522b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f396245bdb8d5e1c75a5bff1988c6875ecb018cc348f9089532a15533946e6c
+oid sha256:1b2b9ceeb1c62606063fec42abb6728182239a71c3611c8bd65d3e5863308d7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.306122448979592,
+  "epoch": 1.6326530612244898,
   "eval_steps": 4,
-  "global_step": 16,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 13.746,
       "eval_steps_per_second": 1.964,
       "step": 16
+    },
+    {
+      "epoch": 1.469387755102041,
+      "grad_norm": NaN,
+      "learning_rate": 7.985792958513931e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "eval_loss": NaN,
+      "eval_runtime": 1.5287,
+      "eval_samples_per_second": 13.738,
+      "eval_steps_per_second": 1.963,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -101,7 +116,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.380622991458304e+16,
+  "total_flos": 2.9840284229566464e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null