Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bff26ead8d4fae2d925671ce76896cd8cef3ff19e435f6aea5480f1b622ccf
+oid sha256:37a551065cba40a64dd9e1916c4ab6d192e0c3448010b6917a95e4b9eb705119
 size 113284112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48a262ab4717a93b850dda3df35a83dbd824bd5d9a7cd9f2001b5ae6b9ddabc3
+oid sha256:e8f76dc89f6f61c94ab16e7ddecd07f9e0d1e2b6fbfdea1669ba4d2f66aab1f8
 size 226735226

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae54447ee58ec850ede3dcf31d65b23cf0633379e56a8331a35d8e2fcc1ac6a3
+oid sha256:a4534cdb02d64f6607a5fa0915639216c9f67c31ade8e59a3486d51659be86e0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc6f08a6602e3be9d6e82a1c4cc04632110d01301d58aa388d3538e776a6b45e
+oid sha256:9099a922bcac85e478413c07bc094bda556811e7816ff1354aff422cee158296
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb13fa6960b609423f1c3aacf1dcb30851fa0f344cb02d979b3249ce17c519c
+oid sha256:1559bf3fc8839acfcb5e179b837f28460a1e1bb17e8e792074204600450c3706
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10deeb728a8fe136ce56355014f9bf0b523bae8072420c637964c7a8a6aabdfb
+oid sha256:b82fab17fcc7c6573e67c38bda62ae9468438bb445c10bf13de9ebe2bab0b27d
 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": 2.5712802410125732,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.8213552361396304,
+  "best_metric": 2.5323638916015625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 1.2397330595482545,
   "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": 24.427,
       "eval_steps_per_second": 6.351,
       "step": 50
+    },
+    {
+      "epoch": 0.837782340862423,
+      "grad_norm": 0.6522903442382812,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.9041,
+      "step": 51
+    },
+    {
+      "epoch": 0.8542094455852156,
+      "grad_norm": 0.635415256023407,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 2.7645,
+      "step": 52
+    },
+    {
+      "epoch": 0.8706365503080082,
+      "grad_norm": 0.6358153820037842,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 2.756,
+      "step": 53
+    },
+    {
+      "epoch": 0.8870636550308009,
+      "grad_norm": 0.5567989945411682,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.6265,
+      "step": 54
+    },
+    {
+      "epoch": 0.9034907597535934,
+      "grad_norm": 0.5632911324501038,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 2.7177,
+      "step": 55
+    },
+    {
+      "epoch": 0.919917864476386,
+      "grad_norm": 0.6154216527938843,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 2.65,
+      "step": 56
+    },
+    {
+      "epoch": 0.9363449691991786,
+      "grad_norm": 0.6227327585220337,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.6083,
+      "step": 57
+    },
+    {
+      "epoch": 0.9527720739219713,
+      "grad_norm": 0.5644506812095642,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 2.6311,
+      "step": 58
+    },
+    {
+      "epoch": 0.9691991786447639,
+      "grad_norm": 0.7271634936332703,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 2.7145,
+      "step": 59
+    },
+    {
+      "epoch": 0.9856262833675564,
+      "grad_norm": 0.9412290453910828,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.5722,
+      "step": 60
+    },
+    {
+      "epoch": 1.0097535934291582,
+      "grad_norm": 1.2142462730407715,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 4.4605,
+      "step": 61
+    },
+    {
+      "epoch": 1.0261806981519508,
+      "grad_norm": 0.6724117994308472,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 2.7223,
+      "step": 62
+    },
+    {
+      "epoch": 1.0426078028747434,
+      "grad_norm": 0.6196894645690918,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.5821,
+      "step": 63
+    },
+    {
+      "epoch": 1.0590349075975358,
+      "grad_norm": 0.6005904078483582,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 2.6824,
+      "step": 64
+    },
+    {
+      "epoch": 1.0754620123203285,
+      "grad_norm": 0.5330093502998352,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 2.5775,
+      "step": 65
+    },
+    {
+      "epoch": 1.091889117043121,
+      "grad_norm": 0.5218847393989563,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.642,
+      "step": 66
+    },
+    {
+      "epoch": 1.1083162217659137,
+      "grad_norm": 0.5194135904312134,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 2.5922,
+      "step": 67
+    },
+    {
+      "epoch": 1.1247433264887063,
+      "grad_norm": 0.5434170365333557,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 2.4498,
+      "step": 68
+    },
+    {
+      "epoch": 1.141170431211499,
+      "grad_norm": 0.5660905838012695,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.6018,
+      "step": 69
+    },
+    {
+      "epoch": 1.1575975359342916,
+      "grad_norm": 0.6597437262535095,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 2.5986,
+      "step": 70
+    },
+    {
+      "epoch": 1.1740246406570842,
+      "grad_norm": 0.8075286746025085,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 2.6485,
+      "step": 71
+    },
+    {
+      "epoch": 1.1904517453798769,
+      "grad_norm": 1.09507155418396,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.577,
+      "step": 72
+    },
+    {
+      "epoch": 1.2068788501026695,
+      "grad_norm": 0.9469268918037415,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 1.7967,
+      "step": 73
+    },
+    {
+      "epoch": 1.2233059548254621,
+      "grad_norm": 0.9090391993522644,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 3.4325,
+      "step": 74
+    },
+    {
+      "epoch": 1.2397330595482545,
+      "grad_norm": 0.629118025302887,
+      "learning_rate": 1e-05,
+      "loss": 2.5815,
+      "step": 75
+    },
+    {
+      "epoch": 1.2397330595482545,
+      "eval_loss": 2.5323638916015625,
+      "eval_runtime": 2.0652,
+      "eval_samples_per_second": 24.21,
+      "eval_steps_per_second": 6.295,
+      "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": 1.055175217250304e+17,
+  "total_flos": 1.582762825875456e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null