Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0c591c2a3e371fbb875624e286bc2a062a77277018cdbf29527c4c7e82d34c
+oid sha256:d61ce4cb025b810a4afd1a4f32914e2909c48a20d3733ba803c453b4b3eebd3d
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288a16e6d9d8c06d39eaaf028ab7ce6ab9c130eeb62c3121161c9ecb57cfd771
+oid sha256:0202e01efe8f13fd7b2c8ee3c96f603708af0ebe0527513b8b210324c785c8c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002767910688748443,
+  "epoch": 0.003690547584997924,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 14.452,
       "eval_steps_per_second": 1.807,
       "step": 15
+    },
+    {
+      "epoch": 0.0033214928264981318,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.003690547584997924,
+      "eval_loss": NaN,
+      "eval_runtime": 631.3699,
+      "eval_samples_per_second": 14.456,
+      "eval_steps_per_second": 1.807,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.146497013481472e+16,
+  "total_flos": 2.861996017975296e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null