Training in progress, step 143, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0286051627e6304668e950769d3d0ae229f4fdf123708da947d2347976384293
+oid sha256:ae56495bc22a94f1c21dfab10ffcb919002e044c09149f05ea612ed2638857fa
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43da8c862366b3e2ebfa7b330e46a7ff17280b46e3a69cf9fb9698df9bd584d4
+oid sha256:64d4968559533980e4aa75808bb9d31ceeb8c578adf5720f38446c96e6557139
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9bc32841f0c3d8bc8ea90b0bc3413eece3c955acd985fe2913112493248454
+oid sha256:a71f60f9bd2ac4332e4682c06bcf0e8b6f23e0f17b0fa94d84f1fe3045e8b4a8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01836871666254548,
+  "epoch": 0.02020558832880003,
   "eval_steps": 13,
-  "global_step": 130,
+  "global_step": 143,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -396,6 +396,42 @@
       "eval_samples_per_second": 50.554,
       "eval_steps_per_second": 6.319,
       "step": 130
+    },
+    {
+      "epoch": 0.01865131230350772,
+      "grad_norm": NaN,
+      "learning_rate": 4.023611372427471e-06,
+      "loss": 0.0,
+      "step": 132
+    },
+    {
+      "epoch": 0.019075205764951076,
+      "grad_norm": NaN,
+      "learning_rate": 2.8058334845816213e-06,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.019499099226394433,
+      "grad_norm": NaN,
+      "learning_rate": 1.8018569652073381e-06,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 0.01992299268783779,
+      "grad_norm": NaN,
+      "learning_rate": 1.016230078838226e-06,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 0.02020558832880003,
+      "eval_loss": NaN,
+      "eval_runtime": 235.8437,
+      "eval_samples_per_second": 50.542,
+      "eval_steps_per_second": 6.318,
+      "step": 143
     }
   ],
   "logging_steps": 3,
@@ -415,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.773092208214016e+16,
+  "total_flos": 3.0504014290354176e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null