Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c2d6c7530a868a4c368dfa792f8950b20bcbe5ea6bca988b21eab7503948d49
+oid sha256:b554910df441f4b870069d597b94dbcd88b164deae37920f7e6c38bce64ac477
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5650086ba9cea3a2f21eb35e293f4f9495d4314840a20e19a7232bc4ba101bc4
+oid sha256:0a848e34108c912191f538d499454fc46a7b8ae4fca8a6715fa9bc363273bf66
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05695301376364499,
+  "epoch": 0.07593735168485999,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,43 @@
       "eval_samples_per_second": 4.092,
       "eval_steps_per_second": 2.046,
       "step": 30
+    },
+    {
+      "epoch": 0.06264831514000949,
+      "grad_norm": NaN,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0664451827242525,
+      "eval_loss": NaN,
+      "eval_runtime": 54.2476,
+      "eval_samples_per_second": 4.092,
+      "eval_steps_per_second": 2.046,
+      "step": 35
+    },
+    {
+      "epoch": 0.068343616516374,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.07403891789273849,
+      "grad_norm": NaN,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.07593735168485999,
+      "eval_loss": NaN,
+      "eval_runtime": 54.2318,
+      "eval_samples_per_second": 4.094,
+      "eval_steps_per_second": 2.047,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -147,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.572377393627136e+16,
+  "total_flos": 2.096503191502848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null