Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9044e6d2214d0e9b55b01f498c588625efba45f76fa710ea1554395b794d6d
+oid sha256:af9e788e546f18a3b27058939ea4434cdddac18c862a33dfd4b9a0f72f9921d8
 size 239452242

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:294def80c0e86e2627232895f7cd12be51fbafc300e62762cd2104710191e91f
+oid sha256:9beca6c32763a3cc8051aec28baf91f153cdbe56a51f49590523253e9deac3c0
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95ca955d9a9a4fe17edeb37a62e75a1e26aa0a8da062df4f479bc6cf74ba889
+oid sha256:b1384fee391a6ad2405d499f49efeb5a52b5f8c74d45b3ac0747ecb863c12d32
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
+oid sha256:3fbc936ac0284bc0c88ce620e190b6b6984693d58131c42013c320d4b2c3a45e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24896265560165975,
+  "epoch": 0.4979253112033195,
   "eval_steps": 15,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,119 @@
       "eval_samples_per_second": 6.02,
       "eval_steps_per_second": 1.535,
       "step": 15
+    },
+    {
+      "epoch": 0.26556016597510373,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.2821576763485477,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.2987551867219917,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.3153526970954357,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.33195020746887965,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.34854771784232363,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.3651452282157676,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.3817427385892116,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.3983402489626556,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.4149377593360996,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.4315352697095436,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.44813278008298757,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.46473029045643155,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.48132780082987553,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.4979253112033195,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.4979253112033195,
+      "eval_loss": NaN,
+      "eval_runtime": 16.7657,
+      "eval_samples_per_second": 6.084,
+      "eval_steps_per_second": 1.551,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -147,7 +260,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.42658589769728e+16,
+  "total_flos": 8.85317179539456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null