Training in progress, step 32, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05f057b66998d3e4d783714a4eb5b106faf33b3d8e6c7c978f3c128839b0dcc
+oid sha256:3f302f5eb248cc4b3060b78746cd8fd8cea698d89120989297de5555ce6fca52
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66e17d758a8617d0a6dde561dd4ee200723e821b4a29963a154e82d549ca080a
+oid sha256:e75c865c58e692a10e06f7dac69d1a74a8975f6df45e232714c0eabbb7322732
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c685a8a34dbecce30163c7b4703580c9fe8e75e3614e8b3101a923890e9ec84e
+oid sha256:0e6acd3296d4fe2aa790f77fb41a20ac6c7ddff695a6b191e7b12de2c5d96193
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2df0fdbab150e4249b8cbacfa9583d996979f81c50ad21e36845ff2d0a6481a
+oid sha256:f13aef1d1bf7ba99ef69fe1590b2ef69392477eb5a7078fbf8d0c5d60ed654f3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3a27f9334ded16cae54ba5fcbb4df41728df37fd481ad7e5e3041feae878c2
+oid sha256:6d1bad4cbb3d4ab52c7cf1ef3c6be2f364014f59c4ffdd445c632138b2257dee
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
+oid sha256:06c69db2db6de56f38ba12b474a491d20087e27dc2893a95d6ac7716476ca645
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.199288256227758,
+  "epoch": 0.2277580071174377,
   "eval_steps": 4,
-  "global_step": 28,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,42 @@
       "eval_samples_per_second": 32.942,
       "eval_steps_per_second": 4.17,
       "step": 28
+    },
+    {
+      "epoch": 0.20640569395017794,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.21352313167259787,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2206405693950178,
+      "grad_norm": NaN,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.2277580071174377,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.2277580071174377,
+      "eval_loss": NaN,
+      "eval_runtime": 7.1955,
+      "eval_samples_per_second": 32.937,
+      "eval_steps_per_second": 4.169,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -286,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.309137575877018e+16,
+  "total_flos": 9.496157229573734e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null