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:e216084ca6f22f5b7f73ad8797fc255d740ac0ec4ddf2715c3ab418eb994dd86
+oid sha256:93687b280ee3b57565942dd5a1b28421a8d93bcd46ef3887a93f8fd0bdefedba
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae73b052a78c6ad39d717529ebc30dc2e686d8ac59b17efdc8983f12f2579d9
+oid sha256:e91d4f88bd79beb1c72af0cdae8374284090306de813be81a6d7814a2419edad
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c01a80664285e7d5390820807762890d7d649ff529d24bc110df999a722c9a
+oid sha256:8066a8fce9d55dac9daad2ad7a95eee3ca41a28c3ca97002ba6d884580d00ab6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b2808b4ec73fbcc9736c08d37c424d724fae72c532d108c617350b4a053207
+oid sha256:7728bbd8c2b314bc5cc878c06847c81f1886c79d3f48803f64a02a522dcee135
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8627af71d0f62077e96e95238bd9db5fe6a62434e89d9f45943a309cab94fd
+oid sha256:8d98e76b5d6907d288fe29a1b37db6d8c6501718be49c5826034cc22d2baf037
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e66227f5c954fd9260d9bc34bb893c3c94a506cf790ea1ef4328d5c9d4b283
+oid sha256:f991b0b770a9b4b790ae4822e231cee53fd7e3e7642bce4020b2ffa8635a6cd5
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 9.109885215759277,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017778172848285517,
+  "best_metric": 8.629364013671875,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03555634569657103,
   "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": 103.018,
       "eval_steps_per_second": 26.785,
       "step": 25
+    },
+    {
+      "epoch": 0.01848929976221694,
+      "grad_norm": 2.8521015644073486,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 8.6864,
+      "step": 26
+    },
+    {
+      "epoch": 0.01920042667614836,
+      "grad_norm": 2.44402813911438,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 8.9519,
+      "step": 27
+    },
+    {
+      "epoch": 0.01991155359007978,
+      "grad_norm": 2.12821102142334,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 9.0138,
+      "step": 28
+    },
+    {
+      "epoch": 0.0206226805040112,
+      "grad_norm": 2.280055522918701,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 8.9783,
+      "step": 29
+    },
+    {
+      "epoch": 0.02133380741794262,
+      "grad_norm": 2.1755645275115967,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 9.1297,
+      "step": 30
+    },
+    {
+      "epoch": 0.02204493433187404,
+      "grad_norm": 1.9306710958480835,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 9.2654,
+      "step": 31
+    },
+    {
+      "epoch": 0.022756061245805464,
+      "grad_norm": 1.8951246738433838,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 9.178,
+      "step": 32
+    },
+    {
+      "epoch": 0.023467188159736883,
+      "grad_norm": 1.691171646118164,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 9.2195,
+      "step": 33
+    },
+    {
+      "epoch": 0.024178315073668303,
+      "grad_norm": 1.6155242919921875,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 9.2252,
+      "step": 34
+    },
+    {
+      "epoch": 0.024889441987599726,
+      "grad_norm": 1.6779975891113281,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 9.3166,
+      "step": 35
+    },
+    {
+      "epoch": 0.025600568901531146,
+      "grad_norm": 1.8211243152618408,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 9.5693,
+      "step": 36
+    },
+    {
+      "epoch": 0.026311695815462565,
+      "grad_norm": 1.7902308702468872,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 9.2382,
+      "step": 37
+    },
+    {
+      "epoch": 0.027022822729393988,
+      "grad_norm": 1.4765057563781738,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 8.6352,
+      "step": 38
+    },
+    {
+      "epoch": 0.027733949643325408,
+      "grad_norm": 1.5339429378509521,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 8.7898,
+      "step": 39
+    },
+    {
+      "epoch": 0.028445076557256827,
+      "grad_norm": 1.5897561311721802,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 8.5414,
+      "step": 40
+    },
+    {
+      "epoch": 0.02915620347118825,
+      "grad_norm": 1.5000419616699219,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 8.7796,
+      "step": 41
+    },
+    {
+      "epoch": 0.02986733038511967,
+      "grad_norm": 1.3983110189437866,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 8.8589,
+      "step": 42
+    },
+    {
+      "epoch": 0.03057845729905109,
+      "grad_norm": 1.286163330078125,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 8.8781,
+      "step": 43
+    },
+    {
+      "epoch": 0.03128958421298251,
+      "grad_norm": 1.181894302368164,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 8.9106,
+      "step": 44
+    },
+    {
+      "epoch": 0.03200071112691393,
+      "grad_norm": 1.153061032295227,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 8.9586,
+      "step": 45
+    },
+    {
+      "epoch": 0.032711838040845355,
+      "grad_norm": 1.2370038032531738,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 9.1853,
+      "step": 46
+    },
+    {
+      "epoch": 0.03342296495477677,
+      "grad_norm": 1.2129719257354736,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 9.0873,
+      "step": 47
+    },
+    {
+      "epoch": 0.034134091868708194,
+      "grad_norm": 1.4687657356262207,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 9.0932,
+      "step": 48
+    },
+    {
+      "epoch": 0.03484521878263962,
+      "grad_norm": 1.6727079153060913,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 9.198,
+      "step": 49
+    },
+    {
+      "epoch": 0.03555634569657103,
+      "grad_norm": 1.8865216970443726,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 9.2588,
+      "step": 50
+    },
+    {
+      "epoch": 0.03555634569657103,
+      "eval_loss": 8.629364013671875,
+      "eval_runtime": 0.4759,
+      "eval_samples_per_second": 105.064,
+      "eval_steps_per_second": 27.317,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 116006898892800.0,
+  "total_flos": 232013797785600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null