Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a64ceeace3ed4a6094bb2890d8409dbab005a0cbf15f173ddd6b91914d55f4
+oid sha256:ac63985102279ffa8d294ecfe7b6e61633086bf401baafe29aca3f4aa76aefb4
 size 61392180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4a3ee778160f42a22e93367025f5b4d76e7fc51b428625824d02549c0d97d5
+oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008573501286025193,
+  "epoch": 0.0017147002572050385,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 10.003,
       "eval_steps_per_second": 5.001,
       "step": 13
+    },
+    {
+      "epoch": 0.0009233001384950207,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0009892501483875222,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010552001582800237,
+      "grad_norm": NaN,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.0011211501681725252,
+      "grad_norm": NaN,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.0011871001780650267,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0012530501879575281,
+      "grad_norm": NaN,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0013190001978500296,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.001384950207742531,
+      "grad_norm": NaN,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014509002176350326,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.001516850227527534,
+      "grad_norm": NaN,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.0015828002374200355,
+      "grad_norm": NaN,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.001648750247312537,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.0017147002572050385,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0017147002572050385,
+      "eval_loss": NaN,
+      "eval_runtime": 2553.7498,
+      "eval_samples_per_second": 10.0,
+      "eval_steps_per_second": 5.0,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.867425071385805e+16,
+  "total_flos": 5.73485014277161e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null