Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:765600a2e8d6be9b0bbfb75caaac7d04dda8e193f6b4feeac34b4f640fce2938
+oid sha256:c6c8452c39e10fd0c315c0b725e832de7ff658839194be93a70ea76e9431b55f
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322a97cf94d0a1106f2a31574761e008a02faf3cb921c0e9d9610b47b898b0fe
+oid sha256:27a4330f6827cd0d22983a258558ff863224f40287062e99bf5d62045e85fc11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012300413956238912,
+  "epoch": 0.01845062093435837,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 17.929,
       "eval_steps_per_second": 8.964,
       "step": 26
+    },
+    {
+      "epoch": 0.014192785334121822,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0429,
+      "step": 30
+    },
+    {
+      "epoch": 0.01845062093435837,
+      "eval_loss": NaN,
+      "eval_runtime": 49.6406,
+      "eval_samples_per_second": 17.929,
+      "eval_steps_per_second": 8.964,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8092588770852864.0,
+  "total_flos": 1.211834359087104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null