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:a00419af52e96f6c0bfbf1c9ab6fd6728dfd885824ad5107ecf4cc4d4f033bce
+oid sha256:2622c75a191a569fc022ae2d66aca825b85f35a11e04998ef7f0f0f8f401f4ec
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e418545b60142a5694d3c508b9c18884ed9ad8cc15f2cc76de50f68b7cf902a
+oid sha256:41b568d8bb0ecbd2fd50569d98e11c5880ee82026a83623608433ba09cf1d1ae
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8223a609ae13a12d247f9d667d5d977331c58ceac1a04ae3cd30b71eaecaa059
+oid sha256:0b278a568d8239303c507ea36f8ff6721647c467b319a5ccaae7a50567818b66
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f354e20e26a44e4aa025877cbd881827ab6639b70ca924c96bb6f2fff6ebe1
+oid sha256:d91b9e27828db842f5d056ae40e93a4ff90d1bc71ebab0befb0bf3c054ce6ebf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6301dd26f6858c9fb974c381e5b7e2da53729647d76b776967a8cd6c973718
+oid sha256:2f08f9f572c1b34e58bc9326049cc32db2efba940eb21cff41614653a4c4a71b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7041219e2b47020ff6e8ccc5afddf000f0d8b55e3def58cd6066d8477c9c7214
+oid sha256:0542f885252366f4c06c1323a312f113c293ef8abc778b68be93b60a204fd024
 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": 0.8404024839401245,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7092198581560284,
+  "best_metric": 0.7745351195335388,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4184397163120568,
   "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": 107.708,
       "eval_steps_per_second": 13.577,
       "step": 25
+    },
+    {
+      "epoch": 0.7375886524822695,
+      "grad_norm": 0.6525234580039978,
+      "learning_rate": 5e-05,
+      "loss": 0.6425,
+      "step": 26
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.37175679206848145,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0672,
+      "step": 27
+    },
+    {
+      "epoch": 0.7943262411347518,
+      "grad_norm": 0.3560580015182495,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9941,
+      "step": 28
+    },
+    {
+      "epoch": 0.8226950354609929,
+      "grad_norm": 0.29323962330818176,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9064,
+      "step": 29
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.2811514437198639,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8322,
+      "step": 30
+    },
+    {
+      "epoch": 0.8794326241134752,
+      "grad_norm": 0.24265116453170776,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7745,
+      "step": 31
+    },
+    {
+      "epoch": 0.9078014184397163,
+      "grad_norm": 0.2871304154396057,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6722,
+      "step": 32
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.31180500984191895,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6407,
+      "step": 33
+    },
+    {
+      "epoch": 0.9645390070921985,
+      "grad_norm": 0.3772461712360382,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5475,
+      "step": 34
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": 0.8375016450881958,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5158,
+      "step": 35
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.6372146606445312,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.7406,
+      "step": 36
+    },
+    {
+      "epoch": 1.049645390070922,
+      "grad_norm": 0.44848495721817017,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9688,
+      "step": 37
+    },
+    {
+      "epoch": 1.0780141843971631,
+      "grad_norm": 0.3469182550907135,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8563,
+      "step": 38
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.3276442885398865,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7992,
+      "step": 39
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "grad_norm": 0.3271907866001129,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7209,
+      "step": 40
+    },
+    {
+      "epoch": 1.1631205673758864,
+      "grad_norm": 0.30662497878074646,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6576,
+      "step": 41
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.3411548435688019,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6093,
+      "step": 42
+    },
+    {
+      "epoch": 1.2198581560283688,
+      "grad_norm": 0.4294974207878113,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5507,
+      "step": 43
+    },
+    {
+      "epoch": 1.24822695035461,
+      "grad_norm": 0.3823366165161133,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.307,
+      "step": 44
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.6564927101135254,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.454,
+      "step": 45
+    },
+    {
+      "epoch": 1.3049645390070923,
+      "grad_norm": 0.41464975476264954,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9198,
+      "step": 46
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.3397634029388428,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8463,
+      "step": 47
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.34161895513534546,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7787,
+      "step": 48
+    },
+    {
+      "epoch": 1.3900709219858156,
+      "grad_norm": 0.2931356132030487,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7096,
+      "step": 49
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "grad_norm": 0.3229428231716156,
+      "learning_rate": 0.0,
+      "loss": 0.672,
+      "step": 50
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "eval_loss": 0.7745351195335388,
+      "eval_runtime": 2.2071,
+      "eval_samples_per_second": 107.834,
+      "eval_steps_per_second": 13.592,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null