Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a34638443619a0074ff65dd497b16f574e80c9fdb420e3c4296436112df978
+oid sha256:0b397010904d2981a0836df557bcee1905ad60498f9639327b19017693880d7c
 size 4644026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5dd73064a7e6156867bfe7cc42d099f9b3ca8a81e8092e75ee1ad1a149c9681
+oid sha256:6370a8be0528273ca811acd9c2bcf74f85b802ea1813f278d9313dd42676b8dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064312e6375f494574ea3d2e75c4bb8dc97a4b36316db34a10f092589094ee40
+oid sha256:8b000d8ec0df62079ef67fc64937bd9acc7a1f4d0e9018e1bef629d1be460950
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.226020094479855e-05,
+  "epoch": 0.0001245204018895971,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 9.999999999999999e-06,
       "loss": 4.7404,
       "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": NaN,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 4.6952,
+      "step": 40
     }
   ],
   "logging_steps": 20,
@@ -21,7 +28,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 276350185052160.0,
+  "total_flos": 414944621529600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null