Training in progress, step 53, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96032390fd76b5881f3520f64469e4c4a585a852acf6f7d2c3133b5854701cfd
+oid sha256:1aa7ccf60318a9b0ad74d9aab98b4ca769636c3b89264b035b4b371ab5c889f4
 size 912734242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3d77e85ef4319d3c71b57607183b1b2cb91cb74c5cafc69ea798287a1fe4e7
+oid sha256:6ae3a3bd5793e8e79f2600d769db33d9a6ecb2bd5fe3a3e3b44ed472c4b18af8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b46be7c94d46cbf3936729b4500eb28aa6241f5015ee42e650f0780bcaa16e
+oid sha256:62186d98e2e1a228b1a77580a02e85af5559d427fe6308d24fc721da049c3720
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8936170212765955,
+  "epoch": 3.0921985815602837,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 53,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,27 @@
       "eval_samples_per_second": 2.973,
       "eval_steps_per_second": 1.586,
       "step": 50
+    },
+    {
+      "epoch": 2.950354609929078,
+      "grad_norm": NaN,
+      "learning_rate": 3.7897451640321323e-07,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 3.0354609929078014,
+      "grad_norm": NaN,
+      "learning_rate": 9.483356314779479e-08,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 3.0921985815602837,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 53
     }
   ],
   "logging_steps": 1,
@@ -395,12 +416,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1492451680256e+17,
+  "total_flos": 1.218199878107136e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null