Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887ff07c00d031a39b0ba1dac930e46878bfe35ea70bcd973da896b8116c8886
+oid sha256:cc6d280ee94e2ebc3e1e0b4d25ebfeaabe02ce2328875fd3c2a100bd834402b2
 size 144985666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3559bb12ea5eec28bb21880a9791c5185d43aa5aa4a2ada420936154e3f09437
+oid sha256:66b7dd0d2dc8c6168a8cba9da0aae3714df9f558b3af757d656d5948b531e01b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012611930886618741,
+  "epoch": 0.0025223861773237483,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 15.302,
       "eval_steps_per_second": 7.66,
       "step": 10
+    },
+    {
+      "epoch": 0.001513431706394249,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0018917896329928112,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0018917896329928112,
+      "eval_loss": NaN,
+      "eval_runtime": 54.6158,
+      "eval_samples_per_second": 15.289,
+      "eval_steps_per_second": 7.653,
+      "step": 15
+    },
+    {
+      "epoch": 0.0022701475595913734,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0025223861773237483,
+      "eval_loss": NaN,
+      "eval_runtime": 54.5584,
+      "eval_samples_per_second": 15.305,
+      "eval_steps_per_second": 7.662,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -66,12 +103,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 400294139658240.0,
+  "total_flos": 800588279316480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null