Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4df1ef4ecc7a0358dc60ae19ce0b9885ef98907fbe5d9592721b955d3fffc30
+oid sha256:7c996069ccaafb7cc010c8a683f9e90998a7147a1194b4b9f4bc6722acfb99be
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba60c260384233e5cb0e7bbfabb0bd75f441fc8b78b5fed933e9ca48341a17ab
+oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00021275803560505727,
+  "epoch": 0.00042551607121011454,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0002553096427260687,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003191370534075859,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003404128569680916,
+      "eval_loss": NaN,
+      "eval_runtime": 2301.8432,
+      "eval_samples_per_second": 8.598,
+      "eval_steps_per_second": 4.299,
+      "step": 16
+    },
+    {
+      "epoch": 0.00038296446408910305,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3515651519938560.0,
+  "total_flos": 7031303039877120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null