Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f4473d0a3f39daee8ddd9c1914da30cb42654dff9e720338270c2980d174ed2
+oid sha256:9ebccb2d5ae68763fb5cf044e2584e6f553a4eadbb148e507580155530c4578d
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b771811ad7a0bcf60e2bba2e1a294ec8700a3d3b280cfd2cd00de3d8c46cbe6c
+oid sha256:050ea566ad4b223a98f4e9f12dfe03bea253d67d5358f523e69ce05bbdf26e76
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008388314432740237,
+  "epoch": 0.0012582471649110354,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 21.325,
       "eval_steps_per_second": 10.663,
       "step": 26
+    },
+    {
+      "epoch": 0.0008710941910922553,
+      "grad_norm": NaN,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.000903356938910487,
+      "grad_norm": NaN,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.0009356196867287187,
+      "grad_norm": NaN,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.0009678824345469504,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.001000145182365182,
+      "grad_norm": NaN,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.0010324079301834137,
+      "grad_norm": NaN,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.0010646706780016455,
+      "grad_norm": NaN,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.001096933425819877,
+      "grad_norm": NaN,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.0011291961736381087,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0011614589214563405,
+      "grad_norm": NaN,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0011937216692745722,
+      "grad_norm": NaN,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.0012259844170928037,
+      "grad_norm": NaN,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.0012582471649110354,
+      "grad_norm": NaN,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0012582471649110354,
+      "eval_loss": NaN,
+      "eval_runtime": 612.0917,
+      "eval_samples_per_second": 21.322,
+      "eval_steps_per_second": 10.662,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7700654944419840.0,
+  "total_flos": 1.162228477722624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null