Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d24b3874a8594c26e49264a461516f9be2949df7bf4de7cea178a29751d70273
+oid sha256:60271aeb35d7b214cf1ab0cf3d47317c0925f2acfa16cb6248224a17960de2fa
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b59a33673f726815018c41edcb801960111b887ff197503bf590a972c10248
+oid sha256:76b9fcc32f21a69b1c52f29f0aeb109a1e91333dcf14b64cf11206f59ddc9604
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0017520805957074025,
+  "epoch": 0.003504161191414805,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 9.265,
       "eval_steps_per_second": 1.159,
       "step": 5
+    },
+    {
+      "epoch": 0.002102496714848883,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0031537450722733244,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.003504161191414805,
+      "eval_loss": NaN,
+      "eval_runtime": 518.5802,
+      "eval_samples_per_second": 9.268,
+      "eval_steps_per_second": 1.159,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.073248506740736e+16,
+  "total_flos": 2.2538218641555456e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null