Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a17e242a38b1c1b535d1ab7f8acd6f0e89e590d0dd05d7a8c6ca3bfe79737f
+oid sha256:888b67fe5aa459333d91ba3f873aee6bf3041273867f04ff81bc7354e8177257
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31ddf03c3777472a31e31670697557906db3af94488f56103c697b428faa0a0
+oid sha256:44c5bb2e7ddee654c81d13cdfc7fefb9c0b7bfe562fef54b732e3486e96349fa
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6d9423c3bde5a7a81310841d28d1f29cb3fad4e24fc19d65fe9bef28aa5e0a
+oid sha256:ee31017f5e573131d929e5b279fa992ddf18745685e6e9898f8eeb99e7a6e653
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f06e3d830720388931a8699bc8d1538e8099b6318aeb0190a81f1bf411eb11e
+oid sha256:cdad6ee80b66c75b843bd9ee713aa6254c7a8b50b444beeb367fde2af8db0b18
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721e9aa82bd50a80e9fff36b309e0ebecd20573ba4ae8833d6b174ccc5ee9b91
+oid sha256:307026b2638f8c73bcec5680b64ef89a856728a4f8d8970782bf46a81049b6ad
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b37d8acd327d0a504e80fcf6257af9ab13af948e572aa9a98348538b86643f15
+oid sha256:ac65f26cb6cdfa6a63d927593506b00a476fbe803ef3ca8eb3acf8195deb721e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0646418333053589,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.053099694676755606,
+  "best_metric": 1.0454801321029663,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.07964954201513341,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 9.587,
       "eval_steps_per_second": 2.493,
       "step": 50
+    },
+    {
+      "epoch": 0.054161688570290724,
+      "grad_norm": 14.636504173278809,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 35.0866,
+      "step": 51
+    },
+    {
+      "epoch": 0.055223682463825835,
+      "grad_norm": 8.89908218383789,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 37.663,
+      "step": 52
+    },
+    {
+      "epoch": 0.056285676357360946,
+      "grad_norm": 54.20383834838867,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 56.8162,
+      "step": 53
+    },
+    {
+      "epoch": 0.05734767025089606,
+      "grad_norm": 16.383342742919922,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 33.3728,
+      "step": 54
+    },
+    {
+      "epoch": 0.05840966414443117,
+      "grad_norm": 12.869865417480469,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 31.2535,
+      "step": 55
+    },
+    {
+      "epoch": 0.05947165803796628,
+      "grad_norm": 11.180938720703125,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 31.5559,
+      "step": 56
+    },
+    {
+      "epoch": 0.06053365193150139,
+      "grad_norm": 11.862079620361328,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 31.4833,
+      "step": 57
+    },
+    {
+      "epoch": 0.06159564582503651,
+      "grad_norm": 12.11618423461914,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 32.5211,
+      "step": 58
+    },
+    {
+      "epoch": 0.06265763971857162,
+      "grad_norm": 15.875182151794434,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 34.1747,
+      "step": 59
+    },
+    {
+      "epoch": 0.06371963361210672,
+      "grad_norm": 19.710519790649414,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 35.3909,
+      "step": 60
+    },
+    {
+      "epoch": 0.06478162750564184,
+      "grad_norm": 17.533973693847656,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 35.6223,
+      "step": 61
+    },
+    {
+      "epoch": 0.06584362139917696,
+      "grad_norm": 22.0009822845459,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 36.3417,
+      "step": 62
+    },
+    {
+      "epoch": 0.06690561529271206,
+      "grad_norm": 29.81911849975586,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 38.5256,
+      "step": 63
+    },
+    {
+      "epoch": 0.06796760918624718,
+      "grad_norm": 7.941569805145264,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 36.4495,
+      "step": 64
+    },
+    {
+      "epoch": 0.06902960307978229,
+      "grad_norm": 13.770777702331543,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 37.7728,
+      "step": 65
+    },
+    {
+      "epoch": 0.0700915969733174,
+      "grad_norm": 51.46889877319336,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 54.747,
+      "step": 66
+    },
+    {
+      "epoch": 0.07115359086685251,
+      "grad_norm": 12.53438949584961,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 30.7638,
+      "step": 67
+    },
+    {
+      "epoch": 0.07221558476038763,
+      "grad_norm": 12.685519218444824,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 32.179,
+      "step": 68
+    },
+    {
+      "epoch": 0.07327757865392275,
+      "grad_norm": 9.042292594909668,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 30.5281,
+      "step": 69
+    },
+    {
+      "epoch": 0.07433957254745785,
+      "grad_norm": 11.904223442077637,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 31.7732,
+      "step": 70
+    },
+    {
+      "epoch": 0.07540156644099297,
+      "grad_norm": 14.069729804992676,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 34.6085,
+      "step": 71
+    },
+    {
+      "epoch": 0.07646356033452807,
+      "grad_norm": 13.064727783203125,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 32.5403,
+      "step": 72
+    },
+    {
+      "epoch": 0.07752555422806319,
+      "grad_norm": 14.395278930664062,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 32.8443,
+      "step": 73
+    },
+    {
+      "epoch": 0.0785875481215983,
+      "grad_norm": 16.937580108642578,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 34.9566,
+      "step": 74
+    },
+    {
+      "epoch": 0.07964954201513341,
+      "grad_norm": 27.33036231994629,
+      "learning_rate": 1e-05,
+      "loss": 37.9665,
+      "step": 75
+    },
+    {
+      "epoch": 0.07964954201513341,
+      "eval_loss": 1.0454801321029663,
+      "eval_runtime": 5.1978,
+      "eval_samples_per_second": 9.619,
+      "eval_steps_per_second": 2.501,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.204505434610729e+17,
+  "total_flos": 1.8034986327841178e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null