Training in progress, step 33, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb939411b0493271436bb1a8bc06226ad9577568a95afb3d55ddc3712e1e012
+oid sha256:a9f3cd7547f8c0f9ba4495b82a561f93d8ae7b57245a9c94a2a6128a0c5eea73
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43f3cb93dee6ee2185ece5e80c88148c1e3b1245ff235aa0f4d77ab9ebca72c
+oid sha256:853bc6b72c7815a0f778850e7db151bcb5aae80de82e4c9f00e324fe5d2ae6e6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594dcf1d063251cca4c3b70569456a468140193c0f517d256489d095068b4748
+oid sha256:4bcb6468c96e42ca9e19eeef69577865d7a693066e16690bd13303c9f6654183
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014344478430545302,
+  "epoch": 0.0027845164012234996,
   "eval_steps": 5,
-  "global_step": 17,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,72 @@
       "eval_samples_per_second": 31.124,
       "eval_steps_per_second": 15.562,
       "step": 15
+    },
+    {
+      "epoch": 0.0015188271279400908,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016875856977112118,
+      "eval_loss": NaN,
+      "eval_runtime": 160.5119,
+      "eval_samples_per_second": 31.088,
+      "eval_steps_per_second": 15.544,
+      "step": 20
+    },
+    {
+      "epoch": 0.0017719649825967724,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020251028372534545,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.002109482122139015,
+      "eval_loss": NaN,
+      "eval_runtime": 160.8054,
+      "eval_samples_per_second": 31.031,
+      "eval_steps_per_second": 15.516,
+      "step": 25
+    },
+    {
+      "epoch": 0.002278240691910136,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0025313785465668178,
+      "grad_norm": NaN,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0025313785465668178,
+      "eval_loss": NaN,
+      "eval_runtime": 159.5505,
+      "eval_samples_per_second": 31.275,
+      "eval_steps_per_second": 15.638,
+      "step": 30
+    },
+    {
+      "epoch": 0.0027845164012234996,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 33
     }
   ],
   "logging_steps": 3,
@@ -88,12 +154,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 306405577850880.0,
+  "total_flos": 594787298181120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null