Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74e32c80a27b88d895bdb1f4578e05687337736870720b59fe44dba58c489ce
+oid sha256:11407487f4da3f4ab302670472ba6d2ebdff710ddcf970e2c332a9dd25dd1443
 size 5962860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34140a7631c27b8f591959a874dda20aba8611a7dac55ebd12c2d17ef586736b
+oid sha256:eb753fce2ff10c0f54d59694fefbb966b94a4c91e74b6c817f99f5900b2e49fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004107479034742427,
+  "epoch": 0.006845798391237378,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "eval_samples_per_second": 44.569,
       "eval_steps_per_second": 22.32,
       "step": 6
+    },
+    {
+      "epoch": 0.004792058873866164,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.005476638712989902,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.00616121855211364,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.00616121855211364,
+      "eval_loss": NaN,
+      "eval_runtime": 13.7866,
+      "eval_samples_per_second": 44.609,
+      "eval_steps_per_second": 22.341,
+      "step": 9
+    },
+    {
+      "epoch": 0.006845798391237378,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 22695651311616.0,
+  "total_flos": 38048591904768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null