Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890d76efb947dc184ea35b28bfd0fe545695a1b8054d80940573ffdd79fcf0f0
+oid sha256:e17ce74019d38f2454569f135d5d3b2391350f53b9cf5393cd3945b7879f8faa
 size 162933396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5645ec7f5c1ef7e1b86925413b40ead61bdcc5a185021fd6d3c941775e12ba
+oid sha256:34ac73ebffc361a29eb6c365a9dad8a79521fe6bef765881cf9ab491bab804d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02414113277623027,
+  "epoch": 0.04828226555246054,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 18.389,
       "eval_steps_per_second": 9.194,
       "step": 13
+    },
+    {
+      "epoch": 0.03714020427112349,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.04828226555246054,
+      "eval_loss": NaN,
+      "eval_runtime": 6.1993,
+      "eval_samples_per_second": 18.389,
+      "eval_steps_per_second": 9.195,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2136511315181568.0,
+  "total_flos": 4273022630363136.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null