Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a060b85c0aa3decd17d624fb4084a1e036b7074d1215946f213fd34c46b169ee
+oid sha256:bfdb8ef99946e39ba1e3517057614667605d1bd34fe98f714770a24f23ee4647
 size 2284938

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3043c5e9269f01e88d7bbedf5c087d49483f225ebdaaa74b04e335c35b8dc3
+oid sha256:0c63f53bc812905ad985f9aa83573bda4734ec93c383860eea2e87d5eb2c382f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
+oid sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00211999152003392,
+  "epoch": 0.0031799872800508796,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,57 @@
       "eval_samples_per_second": 121.407,
       "eval_steps_per_second": 60.734,
       "step": 10
+    },
+    {
+      "epoch": 0.002331990672037312,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.0025439898240407037,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0025439898240407037,
+      "eval_loss": NaN,
+      "eval_runtime": 16.138,
+      "eval_samples_per_second": 123.126,
+      "eval_steps_per_second": 61.594,
+      "step": 12
+    },
+    {
+      "epoch": 0.002755988976044096,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.002967988128047488,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.002967988128047488,
+      "eval_loss": NaN,
+      "eval_runtime": 16.1354,
+      "eval_samples_per_second": 123.146,
+      "eval_steps_per_second": 61.604,
+      "step": 14
+    },
+    {
+      "epoch": 0.0031799872800508796,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -139,12 +190,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 39770426179584.0,
+  "total_flos": 58580762886144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null