Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c82dc709c4d6c75cc2a2ded4e82275a69757df4c6d0a5bf6f7e03696f30b8ab
+oid sha256:243cd2ede3b42282cf22223a0859cb0dcb2572de4f1c3f58b53f455dc31b2db2
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf7bfae0863b52f495a89fc91c5d85c5e29feffa35b0395958864847e5d50fb
+oid sha256:d26869fa048fdf8a1d044eb936fa40ca6721e88f9d0a2442f9a6af39b299dd93
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf207aa118c0fb40da1923f701d115de4544d39e9528102efbb6d6bae04698f2
+oid sha256:57113a2af8df71525575c37ac0bbc1db35c33837d232a828379e162cacc66d3f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb2d215845de80118e7fd140a602d89301ac74bf8f68717029e573bd80cc71c
+oid sha256:45a9bc63108a3ea67dc391b193c248b3ee1d93c00e2b0f669cab38fa2b8e4512
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa7f93407b1bc95b3209752a048868a437c7695d3e79bb16a755db86aca8920
+oid sha256:91eb6e714ae2192c4363862926390c0fcefcdca83a8969551b38b9ebcb0ee8ac
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a1658b37141a6d7edc05be3b7325e5bac2eead4f7d0a482c559ee92ed7b1f7
+oid sha256:dc8fd9518ede07d10683c738bc2fcb5e47e63ee31b62e5fc42fd6ae4a19bb89b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.7268242835998535,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.49607275733774286,
+  "epoch": 0.628358825961141,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 12.34,
       "eval_steps_per_second": 3.208,
       "step": 75
+    },
+    {
+      "epoch": 0.5026870607689128,
+      "grad_norm": 1.0837961435317993,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 1.5649,
+      "step": 76
+    },
+    {
+      "epoch": 0.5093013642000827,
+      "grad_norm": 1.3891311883926392,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 1.5706,
+      "step": 77
+    },
+    {
+      "epoch": 0.5159156676312526,
+      "grad_norm": 0.9055605530738831,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 1.5843,
+      "step": 78
+    },
+    {
+      "epoch": 0.5225299710624225,
+      "grad_norm": 1.7795766592025757,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 1.5982,
+      "step": 79
+    },
+    {
+      "epoch": 0.5291442744935924,
+      "grad_norm": 1.0256783962249756,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 1.6283,
+      "step": 80
+    },
+    {
+      "epoch": 0.5357585779247623,
+      "grad_norm": 1.4087269306182861,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 1.7221,
+      "step": 81
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 1.3582618236541748,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 1.7319,
+      "step": 82
+    },
+    {
+      "epoch": 0.5489871847871021,
+      "grad_norm": 1.3992999792099,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 1.7597,
+      "step": 83
+    },
+    {
+      "epoch": 0.555601488218272,
+      "grad_norm": 1.0967944860458374,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 1.636,
+      "step": 84
+    },
+    {
+      "epoch": 0.5622157916494419,
+      "grad_norm": 1.2128665447235107,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 1.6875,
+      "step": 85
+    },
+    {
+      "epoch": 0.5688300950806118,
+      "grad_norm": 1.3232948780059814,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 1.8021,
+      "step": 86
+    },
+    {
+      "epoch": 0.5754443985117818,
+      "grad_norm": 1.3909993171691895,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 1.8413,
+      "step": 87
+    },
+    {
+      "epoch": 0.5820587019429516,
+      "grad_norm": 1.2057301998138428,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 1.73,
+      "step": 88
+    },
+    {
+      "epoch": 0.5886730053741215,
+      "grad_norm": 0.6822798252105713,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 1.5085,
+      "step": 89
+    },
+    {
+      "epoch": 0.5952873088052915,
+      "grad_norm": 0.7973278760910034,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 1.5389,
+      "step": 90
+    },
+    {
+      "epoch": 0.6019016122364613,
+      "grad_norm": 0.8194143772125244,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 1.563,
+      "step": 91
+    },
+    {
+      "epoch": 0.6085159156676313,
+      "grad_norm": 0.8316376209259033,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 1.5623,
+      "step": 92
+    },
+    {
+      "epoch": 0.6151302190988012,
+      "grad_norm": 1.0160751342773438,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 1.6195,
+      "step": 93
+    },
+    {
+      "epoch": 0.621744522529971,
+      "grad_norm": 1.2698185443878174,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 1.6597,
+      "step": 94
+    },
+    {
+      "epoch": 0.628358825961141,
+      "grad_norm": 0.7779133319854736,
+      "learning_rate": 1e-05,
+      "loss": 1.6596,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.230946832304046e+17,
+  "total_flos": 1.1698376402502943e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null