Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c96d623d748592169e630721b61b23b869a26db526d9d7c948cd48cc5926423e
+oid sha256:81c012bf95a4ba6ebe255a74121333d2d30571a5bc8f8f036a6bfc87e9c1f5b5
 size 37965300

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": 0.04659498207885305,
+  "epoch": 0.0931899641577061,
   "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": 16.471,
       "eval_steps_per_second": 8.235,
       "step": 13
+    },
+    {
+      "epoch": 0.05017921146953405,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.053763440860215055,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.05734767025089606,
+      "grad_norm": NaN,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.06093189964157706,
+      "grad_norm": NaN,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.06810035842293907,
+      "grad_norm": NaN,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.07168458781362007,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.07526881720430108,
+      "grad_norm": NaN,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.07885304659498207,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.08243727598566308,
+      "grad_norm": NaN,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": NaN,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.08960573476702509,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.0931899641577061,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0931899641577061,
+      "eval_loss": NaN,
+      "eval_runtime": 28.5018,
+      "eval_samples_per_second": 16.49,
+      "eval_steps_per_second": 8.245,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3585195902959616e+16,
+  "total_flos": 2.717039180591923e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null