Training in progress, step 12, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5611d10b1dc80593a4bdac7adf240fe7ec3afb8b0341077ac9b221743431d240
+oid sha256:7655c7b685c399d19d65a82d649ccd3cbe037a52d8866bc9d1421efefb1513a6
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fddc7e913fccc4858d959218eae2f6aac98fe04277ee85b74657756755ab2870
+oid sha256:ea12441da8aa5cf6a4fba0da8d5eeb66363e9327da1fdd4b5c2c7b1f575bddda
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fe29649d802f7d8ce4e623123929a93b4808eb8a2c328e1a109d7a9f4c467e
+oid sha256:1fd42fc88546c9b34bc2fbf63a1b59a7f4813abff981c3e9be6ae79921af6f2a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb902d188125a4ef066dade0a74ca2e9fa70cf1044624b225dbb2185e85ddda
+oid sha256:5c1f81faa4b8d80993a6133b2de45d1509d0e26c7e0b7f8ce631a8c84e5145c4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200267047c5b4a65eb479d595575902edeb4e9007b7178ed9fed04b9d89d7e3e
+oid sha256:9dfb88b67d8d33eccaa87f24678bef9c55b93fbb8ffa16b9919e8d6782593f15
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05693950177935943,
+  "epoch": 0.08540925266903915,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 32.947,
       "eval_steps_per_second": 4.171,
       "step": 8
+    },
+    {
+      "epoch": 0.06405693950177936,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0711743772241993,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.07829181494661921,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.08540925266903915,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.08540925266903915,
+      "eval_loss": NaN,
+      "eval_runtime": 7.1961,
+      "eval_samples_per_second": 32.935,
+      "eval_steps_per_second": 4.169,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3740393073934336e+16,
+  "total_flos": 3.5610589610901504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null