Training in progress, step 143, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fea962b166c33ae28a0caf345e11d822b8d0a8c4e89e848b80d811f418af64
+oid sha256:0a3e3cb36c280cfb01ac73a99ddbf9973c2057019fbe14027e45b990306e9157
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641050dc4ba582955532ac44ecda297c53ec5198a21e5aa76396a45365d4d877
+oid sha256:9cb81b7c9730504bc1d548652797affe9958b5f68b25fefb7f810992b4fce281
 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": 1.3265306122448979,
+  "epoch": 1.4591836734693877,
   "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": 36.444,
       "eval_steps_per_second": 4.638,
       "step": 130
+    },
+    {
+      "epoch": 1.346938775510204,
+      "grad_norm": NaN,
+      "learning_rate": 4.023611372427471e-06,
+      "loss": 0.0,
+      "step": 132
+    },
+    {
+      "epoch": 1.3775510204081631,
+      "grad_norm": NaN,
+      "learning_rate": 2.8058334845816213e-06,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 1.4081632653061225,
+      "grad_norm": NaN,
+      "learning_rate": 1.8018569652073381e-06,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 1.4387755102040816,
+      "grad_norm": NaN,
+      "learning_rate": 1.016230078838226e-06,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 1.4591836734693877,
+      "eval_loss": NaN,
+      "eval_runtime": 4.5304,
+      "eval_samples_per_second": 36.421,
+      "eval_steps_per_second": 4.635,
+      "step": 143
     }
   ],
   "logging_steps": 3,
@@ -415,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.537031046627328e+16,
+  "total_flos": 3.8908191965184e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null