Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681a3ce1d9d9dd847912717c1b276b28039b14da8644a778a1c80a13b6c8b8f9
+oid sha256:a25356f1d4da875880fb13346a4087d097ad469aced44a354bf5582f0c250ed7
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca14d646fd395c4881750ce08144a58012e8d4f5ec0fd352727b374a8ce17b3c
+oid sha256:277170e30e72502b504f088c50934ef0e990631bab4fd6da826b4dff0e95079b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019383697813121274,
+  "epoch": 0.02485089463220676,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 26.754,
       "eval_steps_per_second": 3.345,
       "step": 30
+    },
+    {
+      "epoch": 0.019880715705765408,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.019880715705765408,
+      "eval_loss": NaN,
+      "eval_runtime": 507.1417,
+      "eval_samples_per_second": 26.728,
+      "eval_steps_per_second": 3.342,
+      "step": 40
+    },
+    {
+      "epoch": 0.02485089463220676,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.02485089463220676,
+      "eval_loss": NaN,
+      "eval_runtime": 506.5817,
+      "eval_samples_per_second": 26.758,
+      "eval_steps_per_second": 3.346,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.047242266253722e+16,
+  "total_flos": 5.18877213622272e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null