Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fdbef2f8317d7076807030fcfa7feb52ea5ecd2e4adffc8c758803ce6bb7475
+oid sha256:e991794fe3a2eab2baeac20cbac897f1b1cb0c6c7636ab07abdb33b16c041612
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5292396c6085e8fd3c359c9ded6f94f898156446e023768bbc1a95c9a9ebf8
+oid sha256:16942443eb32174380ba4e1cb099b0649f204e6d75dbdc1279ccf562d0c49f0c
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72bc94dedc3738010628a42d72183bf88e7133ceccc924afe008afaa56fa6e07
+oid sha256:ef2d3aa11d8305e166635f9d164efdb40a0986284659eb98a6e35af65903fa1a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c968892b69cd71dbb30a9cad410260c8dd322e8a728cbe1af23f857261b6cd
+oid sha256:91993d212adf5d0c434e06b5ef6b73e078c94fb3bd99932a6c08da343c586cb8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e0853e2608831510f5ef6b037134bfb87d3309fbbe26b243ad7c3f79a605ed
+oid sha256:f1906fed30565dfcf7eca605c8cb04334374eaf5525ad098d27d8ebbd3bef647
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:681f9a6a6971e33065022de9c22e6f9b39edecbcd735bac8b080ff559aea3c55
+oid sha256:0e788f141d2aeb43b3c86fd0770fc1ce56af5eb6bfab67e42ca320d87c264a2e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3192059420211edc26748a07e2699e00ee3be65f92a2cf84ef56d22611d9eb5c
+oid sha256:a8d5f446d81df8b8e6d5d3423a874831fec3d08bffbe4980db71b54ceb3e7bd4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.15416423976421356,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.8602150537634409,
+  "best_metric": 0.14234893023967743,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 1.2903225806451613,
   "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": 19.748,
       "eval_steps_per_second": 1.236,
       "step": 50
+    },
+    {
+      "epoch": 0.8774193548387097,
+      "grad_norm": 1.8466180562973022,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 0.1549,
+      "step": 51
+    },
+    {
+      "epoch": 0.8946236559139785,
+      "grad_norm": 1.785304069519043,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 0.1585,
+      "step": 52
+    },
+    {
+      "epoch": 0.9118279569892473,
+      "grad_norm": 0.2635112702846527,
+      "learning_rate": 4.917330276168208e-05,
+      "loss": 0.1346,
+      "step": 53
+    },
+    {
+      "epoch": 0.9290322580645162,
+      "grad_norm": 1.6671710014343262,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 0.1366,
+      "step": 54
+    },
+    {
+      "epoch": 0.946236559139785,
+      "grad_norm": 2.0387027263641357,
+      "learning_rate": 4.5871032726383386e-05,
+      "loss": 0.1498,
+      "step": 55
+    },
+    {
+      "epoch": 0.9634408602150538,
+      "grad_norm": 0.42053207755088806,
+      "learning_rate": 4.4225768151520694e-05,
+      "loss": 0.1266,
+      "step": 56
+    },
+    {
+      "epoch": 0.9806451612903225,
+      "grad_norm": 0.30820366740226746,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 0.1327,
+      "step": 57
+    },
+    {
+      "epoch": 0.9978494623655914,
+      "grad_norm": 0.22921252250671387,
+      "learning_rate": 4.095597328339452e-05,
+      "loss": 0.1497,
+      "step": 58
+    },
+    {
+      "epoch": 1.0150537634408603,
+      "grad_norm": 0.8588598370552063,
+      "learning_rate": 3.933501846281267e-05,
+      "loss": 0.2963,
+      "step": 59
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 2.0143234729766846,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.1553,
+      "step": 60
+    },
+    {
+      "epoch": 1.049462365591398,
+      "grad_norm": 0.6281954646110535,
+      "learning_rate": 3.612985456190778e-05,
+      "loss": 0.1341,
+      "step": 61
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.46025529503822327,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1248,
+      "step": 62
+    },
+    {
+      "epoch": 1.0838709677419356,
+      "grad_norm": 0.3958461582660675,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 0.1243,
+      "step": 63
+    },
+    {
+      "epoch": 1.1010752688172043,
+      "grad_norm": 0.5285739898681641,
+      "learning_rate": 3.144013755408895e-05,
+      "loss": 0.1274,
+      "step": 64
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 0.5219591856002808,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 0.1439,
+      "step": 65
+    },
+    {
+      "epoch": 1.135483870967742,
+      "grad_norm": 0.28257104754447937,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 0.1273,
+      "step": 66
+    },
+    {
+      "epoch": 1.1526881720430107,
+      "grad_norm": 0.42547574639320374,
+      "learning_rate": 2.693294185106562e-05,
+      "loss": 0.1368,
+      "step": 67
+    },
+    {
+      "epoch": 1.1698924731182796,
+      "grad_norm": 1.2772741317749023,
+      "learning_rate": 2.547882480847461e-05,
+      "loss": 0.1308,
+      "step": 68
+    },
+    {
+      "epoch": 1.1870967741935483,
+      "grad_norm": 1.1020539999008179,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 0.1323,
+      "step": 69
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 0.5631669759750366,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.1461,
+      "step": 70
+    },
+    {
+      "epoch": 1.221505376344086,
+      "grad_norm": 0.28644105792045593,
+      "learning_rate": 2.128356686585282e-05,
+      "loss": 0.1638,
+      "step": 71
+    },
+    {
+      "epoch": 1.238709677419355,
+      "grad_norm": 1.3533546924591064,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 0.1395,
+      "step": 72
+    },
+    {
+      "epoch": 1.2559139784946236,
+      "grad_norm": 1.6018530130386353,
+      "learning_rate": 1.8641182076323148e-05,
+      "loss": 0.1335,
+      "step": 73
+    },
+    {
+      "epoch": 1.2731182795698925,
+      "grad_norm": 0.9039099216461182,
+      "learning_rate": 1.7370711923791567e-05,
+      "loss": 0.1311,
+      "step": 74
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.4418211877346039,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 0.1339,
+      "step": 75
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "eval_loss": 0.14234893023967743,
+      "eval_runtime": 39.6192,
+      "eval_samples_per_second": 19.763,
+      "eval_steps_per_second": 1.237,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2223140042047488e+18,
+  "total_flos": 3.333471006307123e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null