Training in progress, step 28, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe1f8fb02ac1c7e7422ff7b52a3e4d5eb8c6ac17d008a0d3c708e23aac457da
+oid sha256:c05f057b66998d3e4d783714a4eb5b106faf33b3d8e6c7c978f3c128839b0dcc
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e464a5c205fdbca710b6c7b0f62f3e7a32d7ad103273f0b83433ccd346edb1e5
+oid sha256:66e17d758a8617d0a6dde561dd4ee200723e821b4a29963a154e82d549ca080a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:936ee46fc31caf650e5273d2cbccbb91794facecaa31ab719993eb5616659f0e
+oid sha256:c685a8a34dbecce30163c7b4703580c9fe8e75e3614e8b3101a923890e9ec84e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329be30127801777214876c8a2112fc36fcea4d3b34420a1ddfefc37c0e1bbb6
+oid sha256:a2df0fdbab150e4249b8cbacfa9583d996979f81c50ad21e36845ff2d0a6481a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b417bf3c1ef340319ceabf45c1b4f2492a77e9c5d6ab8f628bcf2c8db157c26a
+oid sha256:cf3a27f9334ded16cae54ba5fcbb4df41728df37fd481ad7e5e3041feae878c2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:470670603e8fdc5330cdb9a9152c4fd9c3d8c5a74dd26bffbbb0d869d097eafa
+oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1708185053380783,
+  "epoch": 0.199288256227758,
   "eval_steps": 4,
-  "global_step": 24,
+  "global_step": 28,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,42 @@
       "eval_samples_per_second": 32.937,
       "eval_steps_per_second": 4.169,
       "step": 24
+    },
+    {
+      "epoch": 0.17793594306049823,
+      "grad_norm": NaN,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.18505338078291814,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.19217081850533807,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.199288256227758,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.199288256227758,
+      "eval_loss": NaN,
+      "eval_runtime": 7.1945,
+      "eval_samples_per_second": 32.942,
+      "eval_steps_per_second": 4.17,
+      "step": 28
     }
   ],
   "logging_steps": 1,
@@ -250,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.122117922180301e+16,
+  "total_flos": 8.309137575877018e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null