Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a364db9c7f6f2f5f06abfc82286fd338e35398b9bed16aeeb9e8202728c415
+oid sha256:e55516ae3db2daad1da1290fe8ff509adbd3bfba9a77749770ba02e61f06642a
 size 70674004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0809251b3ae06843370e0b56d0fdc8c7d899d23c2e7fb7d5349f2c443689ae
+oid sha256:68120a49f86666f03bcfc160f2365234645034dcb4bbe38d4111e3b2f824fbb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0019931899343908314,
+  "epoch": 0.002989784901586247,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 9.952,
       "eval_steps_per_second": 4.976,
       "step": 6
+    },
+    {
+      "epoch": 0.002325388256789303,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.002657586579187775,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.002989784901586247,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 1.5199,
+      "step": 9
+    },
+    {
+      "epoch": 0.002989784901586247,
+      "eval_loss": NaN,
+      "eval_runtime": 127.4964,
+      "eval_samples_per_second": 9.945,
+      "eval_steps_per_second": 4.973,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4136398076510208.0,
+  "total_flos": 6204597114765312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null