Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ce1398b6f163a8fd078aa333449f48a9e99fbaa57ffd220caa0898c9ee40b13
+oid sha256:db10c309b10a4761f052c1098da3912b6499476e1827cf8afb6fe44ba4e052e5
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c463b0b879a76c3779e01166a726c45fe69b05a4d89f5e8a3169d262088ea8e8
+oid sha256:190bebcecddcef9484125cdbe6151572a23cdd755815d61454366c6263e697f4
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb2e8cf7a6609edb600058338f0eb75f7956db368a60382330fd3b54537cc6d
+oid sha256:c927d2abe6732bbbb7a2f31e33075ee003e4d703ca53cf76d78237bf9392c9c8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b335d38dd51d951454b465068e9e2bced2ae33ae64a0e34174963e9e462ad6c
+oid sha256:63a5117067d8b57de0c824cec8816b94dca6520348230618f575a86b1e6efe54
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15192cef0b54208441afccbd355be7b0091c22dd9561e1f8afaddb8d351d49fb
+oid sha256:5310aeb7954f66eedda2788c31400a4e38357d8e0360a3ba899ad1e9ef23a6f0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:994551060942d55e8719063144e0fff61b2e5b58811f338518139064b2e45fb6
+oid sha256:df1e1ba83b022c411e8370df23e41163fc4fd87a44da9f3bbc998443bea3510a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8377934694290161,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.19061234214915415,
+  "best_metric": 0.8287712335586548,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3812246842983083,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 144.932,
       "eval_steps_per_second": 18.117,
       "step": 25
+    },
+    {
+      "epoch": 0.19823683583512033,
+      "grad_norm": 0.15700483322143555,
+      "learning_rate": 5e-05,
+      "loss": 0.8346,
+      "step": 26
+    },
+    {
+      "epoch": 0.2058613295210865,
+      "grad_norm": 0.1602972149848938,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8255,
+      "step": 27
+    },
+    {
+      "epoch": 0.21348582320705264,
+      "grad_norm": 0.15739409625530243,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.842,
+      "step": 28
+    },
+    {
+      "epoch": 0.22111031689301883,
+      "grad_norm": 0.15054009854793549,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8599,
+      "step": 29
+    },
+    {
+      "epoch": 0.22873481057898498,
+      "grad_norm": 0.1502337008714676,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.817,
+      "step": 30
+    },
+    {
+      "epoch": 0.23635930426495116,
+      "grad_norm": 0.14839516580104828,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8335,
+      "step": 31
+    },
+    {
+      "epoch": 0.24398379795091732,
+      "grad_norm": 0.1509093940258026,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8419,
+      "step": 32
+    },
+    {
+      "epoch": 0.2516082916368835,
+      "grad_norm": 0.15149198472499847,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8169,
+      "step": 33
+    },
+    {
+      "epoch": 0.25923278532284966,
+      "grad_norm": 0.15918795764446259,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.859,
+      "step": 34
+    },
+    {
+      "epoch": 0.26685727900881584,
+      "grad_norm": 0.1778258979320526,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8393,
+      "step": 35
+    },
+    {
+      "epoch": 0.27448177269478197,
+      "grad_norm": 0.19277341663837433,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8147,
+      "step": 36
+    },
+    {
+      "epoch": 0.28210626638074815,
+      "grad_norm": 0.19680185616016388,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.78,
+      "step": 37
+    },
+    {
+      "epoch": 0.28973076006671433,
+      "grad_norm": 0.12966406345367432,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8441,
+      "step": 38
+    },
+    {
+      "epoch": 0.29735525375268046,
+      "grad_norm": 0.12343523651361465,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8377,
+      "step": 39
+    },
+    {
+      "epoch": 0.30497974743864664,
+      "grad_norm": 0.12981387972831726,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8426,
+      "step": 40
+    },
+    {
+      "epoch": 0.3126042411246128,
+      "grad_norm": 0.13032592833042145,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.84,
+      "step": 41
+    },
+    {
+      "epoch": 0.320228734810579,
+      "grad_norm": 0.1364886462688446,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8459,
+      "step": 42
+    },
+    {
+      "epoch": 0.32785322849654513,
+      "grad_norm": 0.13743382692337036,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8038,
+      "step": 43
+    },
+    {
+      "epoch": 0.3354777221825113,
+      "grad_norm": 0.14321595430374146,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8594,
+      "step": 44
+    },
+    {
+      "epoch": 0.3431022158684775,
+      "grad_norm": 0.139565110206604,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8038,
+      "step": 45
+    },
+    {
+      "epoch": 0.3507267095544436,
+      "grad_norm": 0.15720701217651367,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8524,
+      "step": 46
+    },
+    {
+      "epoch": 0.3583512032404098,
+      "grad_norm": 0.16059865057468414,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8119,
+      "step": 47
+    },
+    {
+      "epoch": 0.365975696926376,
+      "grad_norm": 0.1649278700351715,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7992,
+      "step": 48
+    },
+    {
+      "epoch": 0.3736001906123422,
+      "grad_norm": 0.17470909655094147,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8197,
+      "step": 49
+    },
+    {
+      "epoch": 0.3812246842983083,
+      "grad_norm": 0.21436592936515808,
+      "learning_rate": 0.0,
+      "loss": 0.8206,
+      "step": 50
+    },
+    {
+      "epoch": 0.3812246842983083,
+      "eval_loss": 0.8287712335586548,
+      "eval_runtime": 12.2583,
+      "eval_samples_per_second": 144.228,
+      "eval_steps_per_second": 18.029,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.956700382396416e+16,
+  "total_flos": 5.913400764792832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null