Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d114e1eba96225c2266f16c86322870912d29be5a4e82f4d69bead7181bd6d
+oid sha256:929a8af8e27f62639075bdeea688a46e24e34fc94e58fa753777b1dd88591817
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b75e4d5409cbbf130113770c587a54e3889a162f0ccdbd5e0c85f746a9026c5
+oid sha256:79edf61b4fe2c56808485160c943c488095f3d4171f1a7d68467fcfb8ec251d8
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1cef257c57ee5e3ef9f387fdf399088f5af86c0b0614fa532e4d4ccc80887f
+oid sha256:7ad1349adb94f706f06429ed068c830a154214fce15b2a1aca2b3e8078b4e60e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6417112d0fae2bc269841372c028c9d5261a7c66af1bbfa10966520f5f37f835
+oid sha256:10812802173bdc9f372d285a96389fc081fc7d318ad29ad1832d8cbe9dc0b4fb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ebb34a8af752c2a58359b3b19276da13d2924a85774e6b115ca7e443eb1253
+oid sha256:6ce6bb83e23e624faa7d4d0f0d916aa2bfb398e54c45dc8ab27f6276d8d4836b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d7d7df9ab90a0078028402c135bd1955247e40fbb2bbf9740604327e4ad6f51
+oid sha256:3d3d30cece1e3ffca9dbba541c8e005ad3300bb9a15b32d293b6da038ae185ae
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d86c14ba8318910aefeec760794a93d9c3bde8861e35789ea66016a8d43ece
+oid sha256:77a3132902dff05847d42068955a2890663d28a5047f2e7ac187fce7795a5d4b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.38400650024414,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1695906432748537,
+  "best_metric": 10.37548828125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.3391812865497075,
   "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": 639.565,
       "eval_steps_per_second": 166.287,
       "step": 25
+    },
+    {
+      "epoch": 1.2163742690058479,
+      "grad_norm": 0.11057508736848831,
+      "learning_rate": 7.274601348009935e-05,
+      "loss": 10.1665,
+      "step": 26
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.11977867782115936,
+      "learning_rate": 7.062873637801692e-05,
+      "loss": 10.8457,
+      "step": 27
+    },
+    {
+      "epoch": 1.3099415204678362,
+      "grad_norm": 0.09831052273511887,
+      "learning_rate": 6.847134053380112e-05,
+      "loss": 10.5002,
+      "step": 28
+    },
+    {
+      "epoch": 1.3567251461988303,
+      "grad_norm": 0.09686669707298279,
+      "learning_rate": 6.627936395164243e-05,
+      "loss": 10.2253,
+      "step": 29
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 0.09972165524959564,
+      "learning_rate": 6.40584334039897e-05,
+      "loss": 10.1396,
+      "step": 30
+    },
+    {
+      "epoch": 1.4502923976608186,
+      "grad_norm": 0.10765210539102554,
+      "learning_rate": 6.181424998770595e-05,
+      "loss": 9.7169,
+      "step": 31
+    },
+    {
+      "epoch": 1.4970760233918128,
+      "grad_norm": 0.12939834594726562,
+      "learning_rate": 5.955257448943445e-05,
+      "loss": 10.9171,
+      "step": 32
+    },
+    {
+      "epoch": 1.543859649122807,
+      "grad_norm": 0.12637734413146973,
+      "learning_rate": 5.727921259774208e-05,
+      "loss": 10.602,
+      "step": 33
+    },
+    {
+      "epoch": 1.590643274853801,
+      "grad_norm": 0.1105811670422554,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.6176,
+      "step": 34
+    },
+    {
+      "epoch": 1.6374269005847952,
+      "grad_norm": 0.11131985485553741,
+      "learning_rate": 5.2720787402257935e-05,
+      "loss": 10.2836,
+      "step": 35
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.11741997301578522,
+      "learning_rate": 5.044742551056556e-05,
+      "loss": 10.0027,
+      "step": 36
+    },
+    {
+      "epoch": 1.7309941520467835,
+      "grad_norm": 0.14288607239723206,
+      "learning_rate": 4.8185750012294065e-05,
+      "loss": 10.4621,
+      "step": 37
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.12223335355520248,
+      "learning_rate": 4.594156659601029e-05,
+      "loss": 10.6583,
+      "step": 38
+    },
+    {
+      "epoch": 1.8245614035087718,
+      "grad_norm": 0.12245681881904602,
+      "learning_rate": 4.372063604835758e-05,
+      "loss": 9.8662,
+      "step": 39
+    },
+    {
+      "epoch": 1.871345029239766,
+      "grad_norm": 0.12315724790096283,
+      "learning_rate": 4.152865946619889e-05,
+      "loss": 10.76,
+      "step": 40
+    },
+    {
+      "epoch": 1.9181286549707601,
+      "grad_norm": 0.12260238081216812,
+      "learning_rate": 3.93712636219831e-05,
+      "loss": 10.3994,
+      "step": 41
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "grad_norm": 0.15077726542949677,
+      "learning_rate": 3.725398651990067e-05,
+      "loss": 11.4694,
+      "step": 42
+    },
+    {
+      "epoch": 2.0116959064327484,
+      "grad_norm": 0.19197246432304382,
+      "learning_rate": 3.518226317990646e-05,
+      "loss": 15.752,
+      "step": 43
+    },
+    {
+      "epoch": 2.0584795321637426,
+      "grad_norm": 0.12943069636821747,
+      "learning_rate": 3.3161411686101364e-05,
+      "loss": 10.6442,
+      "step": 44
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.11681056767702103,
+      "learning_rate": 3.119661953528671e-05,
+      "loss": 10.0928,
+      "step": 45
+    },
+    {
+      "epoch": 2.152046783625731,
+      "grad_norm": 0.12141174077987671,
+      "learning_rate": 2.9292930320734335e-05,
+      "loss": 10.3879,
+      "step": 46
+    },
+    {
+      "epoch": 2.198830409356725,
+      "grad_norm": 0.12950986623764038,
+      "learning_rate": 2.745523078535517e-05,
+      "loss": 10.1063,
+      "step": 47
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.14073993265628815,
+      "learning_rate": 2.568823827750001e-05,
+      "loss": 9.7249,
+      "step": 48
+    },
+    {
+      "epoch": 2.2923976608187133,
+      "grad_norm": 0.14041155576705933,
+      "learning_rate": 2.39964886415941e-05,
+      "loss": 11.2327,
+      "step": 49
+    },
+    {
+      "epoch": 2.3391812865497075,
+      "grad_norm": 0.14114905893802643,
+      "learning_rate": 2.2384324574689612e-05,
+      "loss": 10.3466,
+      "step": 50
+    },
+    {
+      "epoch": 2.3391812865497075,
+      "eval_loss": 10.37548828125,
+      "eval_runtime": 0.0757,
+      "eval_samples_per_second": 660.475,
+      "eval_steps_per_second": 171.723,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null