Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a7c5fa4c1a040a5b4d74e58dbf409dea914605f590b86e231084e88d2a67609
+oid sha256:15e3e3bbb0d91cdcda31de51f19820f22c2392d01fa90afff6bb1bc8781b5f2d
 size 713496

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca99bebeea385ce2c1d4db38b17f7a71d082f2093a6dc4945fbf7655d2c5b44a
+oid sha256:2a6258672381d102671acb4905764cd2ce59f8b7e086690b4eb2df044a5bac1a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001110307166477606,
+  "epoch": 0.00014804095553034747,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 105.227,
       "eval_steps_per_second": 105.227,
       "step": 15
+    },
+    {
+      "epoch": 0.00011843276442427798,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.00012583481220079535,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.00013323685997731273,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0001406389077538301,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.00014804095553034747,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.00014804095553034747,
+      "eval_loss": NaN,
+      "eval_runtime": 168.5642,
+      "eval_samples_per_second": 168.731,
+      "eval_steps_per_second": 168.731,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4017763123200.0,
+  "total_flos": 5357017497600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null