Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b5409ec054d8ab0426892b0e7f6e90ed3abed0101746abf58e53e1ee3c87a3
+oid sha256:04542a8a8f4997877cf19de2f2f40075d162e9d03e558b378e1174e5c6d72b24
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647803204aa5c083c8465f752eaf1dde16e977abdabd5b93587576a380b8cbdc
+oid sha256:434330aa91d3168fb439501decd09101b4d4a95add94876d0a7a56280ac3a8af
 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": 0.03378817413905133,
+  "epoch": 0.06757634827810266,
   "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": 50.56,
       "eval_steps_per_second": 25.435,
       "step": 13
+    },
+    {
+      "epoch": 0.05198180636777128,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.06757634827810266,
+      "eval_loss": NaN,
+      "eval_runtime": 2.961,
+      "eval_samples_per_second": 55.049,
+      "eval_steps_per_second": 27.694,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 711871325798400.0,
+  "total_flos": 1328826474823680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null