Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e385624cce8eb37217567e940d1222196a90e86e3dfcd9b0ea0068b0e6dd5f14
+oid sha256:ec67845785cbb945c53971f42bac51e67bad2e5a31c63fcfde08cafc7a759bcf
 size 60247362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a721623c09a960decabec24ee0a27ef73ed5424f446e55c11a3e65119e63ccf
+oid sha256:6a1758f8925c393aa5d58480f63611632e837d199626f533e42ddecd94e7105b
 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": 0.004264846998613925,
+  "epoch": 0.00852969399722785,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,116 @@
       "eval_samples_per_second": 19.949,
       "eval_steps_per_second": 9.974,
       "step": 10
+    },
+    {
+      "epoch": 0.0046913316984753175,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.00511781639833671,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.00511781639833671,
+      "eval_loss": NaN,
+      "eval_runtime": 49.5221,
+      "eval_samples_per_second": 19.951,
+      "eval_steps_per_second": 9.975,
+      "step": 12
+    },
+    {
+      "epoch": 0.005544301098198102,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.0059707857980594945,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0059707857980594945,
+      "eval_loss": NaN,
+      "eval_runtime": 49.531,
+      "eval_samples_per_second": 19.947,
+      "eval_steps_per_second": 9.974,
+      "step": 14
+    },
+    {
+      "epoch": 0.006397270497920887,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.006823755197782279,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.006823755197782279,
+      "eval_loss": NaN,
+      "eval_runtime": 49.5109,
+      "eval_samples_per_second": 19.955,
+      "eval_steps_per_second": 9.978,
+      "step": 16
+    },
+    {
+      "epoch": 0.007250239897643672,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.007676724597505065,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.007676724597505065,
+      "eval_loss": NaN,
+      "eval_runtime": 49.5165,
+      "eval_samples_per_second": 19.953,
+      "eval_steps_per_second": 9.976,
+      "step": 18
+    },
+    {
+      "epoch": 0.008103209297366456,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.00852969399722785,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.00852969399722785,
+      "eval_loss": NaN,
+      "eval_runtime": 49.5454,
+      "eval_samples_per_second": 19.941,
+      "eval_steps_per_second": 9.971,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -139,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1265549023641600.0,
+  "total_flos": 2531098047283200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null