Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66472385d43d815e5cb5e2c50cac3ce7b887080c0eb53b6922dc899a81b16cb
+oid sha256:6608f54b8fab58607e7cdf712408ba68f9a0c67466a9df5d813be3223c4b1838
 size 579417298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f16763b0290846d4e3085dfa1c189d3d54ff7140175584d011a2ab8e589792
+oid sha256:659b69c6618f2f94ffe75b9627fc86c42e53fcaf530f398907a17c94553b9baf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000899088548983468,
+  "epoch": 0.001348632823475202,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 6.117,
       "eval_steps_per_second": 3.059,
       "step": 20
+    },
+    {
+      "epoch": 0.0009440429764326414,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010789062587801617,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.001123860686229335,
+      "eval_loss": NaN,
+      "eval_runtime": 2054.9787,
+      "eval_samples_per_second": 4.558,
+      "eval_steps_per_second": 2.279,
+      "step": 25
+    },
+    {
+      "epoch": 0.001213769541127682,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.001348632823475202,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.001348632823475202,
+      "eval_loss": NaN,
+      "eval_runtime": 1397.7655,
+      "eval_samples_per_second": 6.701,
+      "eval_steps_per_second": 3.351,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.46143835062272e+16,
+  "total_flos": 2.159681118142464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null