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:b95049219a13bbc11230849ac3a343308d344260011ee4e1514c259254c54d47
+oid sha256:187bd66d90f074644b27a69f919f3db65281d59b929bf6b8b1d3d192cd8f96f1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82bcae6d043facfd90340524b3b8642156381a293f95e4da20c8c1326e6625a
+oid sha256:33690991c4a267d0cd5509f2b2958188c6b9293c3e00831d5d3c920a9ab14774
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b47f9e3f5d9a1b1a4f07093346b7b1dd918ba5649711aef1b8132c6f0d43b1b
+oid sha256:7afe554c98fdec947e3ddabb2e390b48f389983f4ca1cfc174e0c32251154a41
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14aa92035b407f63b0e40965392304e93b6b4a1977b0199e30acd4f9cfff8b7c
+oid sha256:a505d5076d75ff38408347597e66f6be62a1693a2412d8b5afdad0ef8e045e7a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ddc93711afd3bdc7ab0506e6b15ab8f754590f3d69d2112830228fb6e6eca9
+oid sha256:658ff55100ee27a32f32b5a5467aa3f9ecbfd1340d036c5ce91a46005ca48a81
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa1af1f0355e7b745fc8014d4f00767a707bf342f1ca33d154bf4ad2da5b236c
+oid sha256:ff475b073b0351cc27e905043de1cc6faf67b890232176813d0553ad86460dea
 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": 0.06616319715976715,
   "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": 10.504,
       "eval_steps_per_second": 2.731,
       "step": 75
+    },
+    {
+      "epoch": 0.5026870607689128,
+      "grad_norm": 25.12753677368164,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 1.399,
+      "step": 76
+    },
+    {
+      "epoch": 0.5093013642000827,
+      "grad_norm": 28.479808807373047,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 3.5418,
+      "step": 77
+    },
+    {
+      "epoch": 0.5159156676312526,
+      "grad_norm": 55.195472717285156,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 3.0269,
+      "step": 78
+    },
+    {
+      "epoch": 0.5225299710624225,
+      "grad_norm": 27.613985061645508,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 2.3188,
+      "step": 79
+    },
+    {
+      "epoch": 0.5291442744935924,
+      "grad_norm": 27.04929542541504,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 2.259,
+      "step": 80
+    },
+    {
+      "epoch": 0.5357585779247623,
+      "grad_norm": 21.039297103881836,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 1.7836,
+      "step": 81
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 30.927331924438477,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 3.1101,
+      "step": 82
+    },
+    {
+      "epoch": 0.5489871847871021,
+      "grad_norm": 24.94784927368164,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 2.78,
+      "step": 83
+    },
+    {
+      "epoch": 0.555601488218272,
+      "grad_norm": 25.634151458740234,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 2.8305,
+      "step": 84
+    },
+    {
+      "epoch": 0.5622157916494419,
+      "grad_norm": 23.10271644592285,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 2.1801,
+      "step": 85
+    },
+    {
+      "epoch": 0.5688300950806118,
+      "grad_norm": 28.00276756286621,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 3.5865,
+      "step": 86
+    },
+    {
+      "epoch": 0.5754443985117818,
+      "grad_norm": 19.719558715820312,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 2.0314,
+      "step": 87
+    },
+    {
+      "epoch": 0.5820587019429516,
+      "grad_norm": 29.483997344970703,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 2.515,
+      "step": 88
+    },
+    {
+      "epoch": 0.5886730053741215,
+      "grad_norm": 32.51318359375,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 1.9051,
+      "step": 89
+    },
+    {
+      "epoch": 0.5952873088052915,
+      "grad_norm": 22.37510108947754,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 2.1287,
+      "step": 90
+    },
+    {
+      "epoch": 0.6019016122364613,
+      "grad_norm": 29.376789093017578,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 2.541,
+      "step": 91
+    },
+    {
+      "epoch": 0.6085159156676313,
+      "grad_norm": 22.571348190307617,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 1.9258,
+      "step": 92
+    },
+    {
+      "epoch": 0.6151302190988012,
+      "grad_norm": 37.25621032714844,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 3.2117,
+      "step": 93
+    },
+    {
+      "epoch": 0.621744522529971,
+      "grad_norm": 25.335430145263672,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 1.5901,
+      "step": 94
+    },
+    {
+      "epoch": 0.628358825961141,
+      "grad_norm": 27.5488224029541,
+      "learning_rate": 1e-05,
+      "loss": 3.1688,
+      "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": 8.487032007426048e+17,
+  "total_flos": 1.0750240542739661e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null