Training in progress, step 130, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cab66a9ac6a7915e9514675876bc4722ab7dda5a154da7acb92ef39161c1b30
+oid sha256:27fea962b166c33ae28a0caf345e11d822b8d0a8c4e89e848b80d811f418af64
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb88087a989efdb67ff97d3da25401e541aeeb31f6e8cdd767f7fb901fb5acc
+oid sha256:641050dc4ba582955532ac44ecda297c53ec5198a21e5aa76396a45365d4d877
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a9f08177ba433a82ec0fa599b737a453ff55e83dd9d31c6fddaf5bc4b0a0b3
+oid sha256:4f9bc32841f0c3d8bc8ea90b0bc3413eece3c955acd985fe2913112493248454
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.193877551020408,
+  "epoch": 1.3265306122448979,
   "eval_steps": 13,
-  "global_step": 117,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -360,6 +360,42 @@
       "eval_samples_per_second": 36.443,
       "eval_steps_per_second": 4.638,
       "step": 117
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": NaN,
+      "learning_rate": 1.090842587659851e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.2551020408163265,
+      "grad_norm": NaN,
+      "learning_rate": 8.899896227604509e-06,
+      "loss": 0.0,
+      "step": 123
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": NaN,
+      "learning_rate": 7.077560319906695e-06,
+      "loss": 0.0,
+      "step": 126
+    },
+    {
+      "epoch": 1.316326530612245,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 129
+    },
+    {
+      "epoch": 1.3265306122448979,
+      "eval_loss": NaN,
+      "eval_runtime": 4.5275,
+      "eval_samples_per_second": 36.444,
+      "eval_steps_per_second": 4.638,
+      "step": 130
     }
   ],
   "logging_steps": 3,
@@ -379,7 +415,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.183242896736256e+16,
+  "total_flos": 3.537031046627328e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null