Training in progress, step 34, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5db45574d4a8c70773208b47b767b809d492505b83768f43814580c1122cb2
+oid sha256:38bb48413e7fec321d31d234a33b486eafc285ce7ed9fd00b27909a34898662e
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a35ffc5a2035c2bb835d48f31dca7f4b4744ac86d0daf6a89e43471f43f751
+oid sha256:57ad4d886bbce296ef82d35e7b35217a219d13c344b8f35284b8759501aa1ff1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0abe1a027b3fea2bf654a1c387b6eb2241fa486bab4a282d3a0e829c4308c91
+oid sha256:2e1983b20d7ce0214623b79adb071ed1f5c168cabcab4cc0ff2c0c61c63ddce9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0033919652822376996,
+  "epoch": 0.006783930564475399,
   "eval_steps": 50,
-  "global_step": 17,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -134,6 +134,125 @@
       "learning_rate": 0.00012749999999999998,
       "loss": 0.0,
       "step": 17
+    },
+    {
+      "epoch": 0.0035914926517810935,
+      "grad_norm": NaN,
+      "learning_rate": 0.000135,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0037910200213244877,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001425,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.003990547390867882,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.004190074760411276,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014998857713672935,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.00438960212995467,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014995431202643217,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.004589129499498064,
+      "grad_norm": NaN,
+      "learning_rate": 0.000149897215106593,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.004788656869041458,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001498173037694868,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.004988184238584852,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001497146023568809,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.005187711608128246,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014958914215262048,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.005387238977671641,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014944096137309914,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0055867663472150345,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014927010515561776,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.005786293716758428,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014907662554463532,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.005985821086301822,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001488605814759156,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.006185348455845217,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014862203875857477,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.006384875825388611,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001483610700550354,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.0065844031949320045,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014807775485889264,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.006783930564475399,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001477721794706997,
+      "loss": 0.0,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -153,7 +272,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0145742149438669e+17,
+  "total_flos": 2.0291484298877338e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null