Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9e788e546f18a3b27058939ea4434cdddac18c862a33dfd4b9a0f72f9921d8
+oid sha256:c3b0162c125dace0461332123e8c7d602462e84e158ad2d3f071bbc125b34b8d
 size 239452242

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9beca6c32763a3cc8051aec28baf91f153cdbe56a51f49590523253e9deac3c0
+oid sha256:56e0b4692f0d79aa027250daa798b9b99aa2daab99fce81150537a9623556468
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1384fee391a6ad2405d499f49efeb5a52b5f8c74d45b3ac0747ecb863c12d32
+oid sha256:a7c19a532ddf743881461eea886de51a0451550ba062c994babb62565733b22d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbc936ac0284bc0c88ce620e190b6b6984693d58131c42013c320d4b2c3a45e
+oid sha256:7e94f4caf902c120d48372da3bb1cf8d147f3ddef7262ea875dbd118eb698ece
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4979253112033195,
+  "epoch": 0.7468879668049793,
   "eval_steps": 15,
-  "global_step": 30,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,119 @@
       "eval_samples_per_second": 6.084,
       "eval_steps_per_second": 1.551,
       "step": 30
+    },
+    {
+      "epoch": 0.5145228215767634,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.5311203319502075,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.5477178423236515,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.5643153526970954,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.5809128630705395,
+      "grad_norm": NaN,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.5975103734439834,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.6141078838174274,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.6307053941908713,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.6473029045643154,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.6639004149377593,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.6804979253112033,
+      "grad_norm": NaN,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.6970954356846473,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.7136929460580913,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.7302904564315352,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.7468879668049793,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.7468879668049793,
+      "eval_loss": NaN,
+      "eval_runtime": 16.8908,
+      "eval_samples_per_second": 6.039,
+      "eval_steps_per_second": 1.539,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -260,7 +373,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.85317179539456e+16,
+  "total_flos": 1.327975769309184e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null