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:def1a51a308008829acbcdb0f385a2bc1d5565085f04593338bde30384faade0
+oid sha256:f2d7259fa088b17119edf9507f5fa5f412533f5d7248d22589c6de653b7e16eb
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:460fde84ee226f3d4a07bcd0732ce5e161a0a01df3e9be73d5298b4a87e80bd3
+oid sha256:52e42c9ff602c1bddf06cb5014fdbd6cebcb5199c4bfab1ee6bd4c7c22bcbf8f
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9858fd98e669f0ca689f61f793b4b19851ed430df3dce9f6065f95a97dcfb0ab
+oid sha256:09152e6fc8a67ee0c72434f98f14746f06d33c1f278d729ae60ff2ac5c5d6d5f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b23ab703604fdd5bf3efa3688c186ecc0ed68fe7dce07dc788e5d6483bafbd3
+oid sha256:1c608551bba1bad46c968c985f6df43ede8d07c433ff6c8965ce863be38b5e07
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2608e2e0fb7ac69593bc4e5ec5d85c55ff857e9d9c49427071665cd1cd468ebc
+oid sha256:087605d3289d324189b4c91b42798ae3abb1f774bdbe31c966f1ff8a234b7dd1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29edb0290ab9a3d774de5d5527b49f700e9fc1cab3a7771a5f30228d8960cd7c
+oid sha256:6ab9ae8254fec2205101469b5dcf47d874fa65f80d664c079eb3ae1df821ee2d
 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": 11.925982475280762,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.04246585037865383,
+  "epoch": 0.05379007714629486,
   "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": 287.402,
       "eval_steps_per_second": 74.725,
       "step": 75
+    },
+    {
+      "epoch": 0.043032061717035885,
+      "grad_norm": 0.019447388127446175,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 11.9267,
+      "step": 76
+    },
+    {
+      "epoch": 0.043598273055417934,
+      "grad_norm": 0.024625686928629875,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 11.9275,
+      "step": 77
+    },
+    {
+      "epoch": 0.04416448439379998,
+      "grad_norm": 0.024972781538963318,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 11.9273,
+      "step": 78
+    },
+    {
+      "epoch": 0.04473069573218204,
+      "grad_norm": 0.028384722769260406,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 11.9259,
+      "step": 79
+    },
+    {
+      "epoch": 0.04529690707056409,
+      "grad_norm": 0.031045373529195786,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 11.926,
+      "step": 80
+    },
+    {
+      "epoch": 0.04586311840894614,
+      "grad_norm": 0.03209468722343445,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 11.9275,
+      "step": 81
+    },
+    {
+      "epoch": 0.04642932974732819,
+      "grad_norm": 0.03293868526816368,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 11.9275,
+      "step": 82
+    },
+    {
+      "epoch": 0.04699554108571024,
+      "grad_norm": 0.03368574380874634,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 11.9272,
+      "step": 83
+    },
+    {
+      "epoch": 0.047561752424092295,
+      "grad_norm": 0.03013777732849121,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 11.9262,
+      "step": 84
+    },
+    {
+      "epoch": 0.04812796376247434,
+      "grad_norm": 0.03828248009085655,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 11.924,
+      "step": 85
+    },
+    {
+      "epoch": 0.04869417510085639,
+      "grad_norm": 0.04111775755882263,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 11.9271,
+      "step": 86
+    },
+    {
+      "epoch": 0.04926038643923845,
+      "grad_norm": 0.04474611580371857,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 11.9244,
+      "step": 87
+    },
+    {
+      "epoch": 0.049826597777620496,
+      "grad_norm": 0.027258913964033127,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 11.9264,
+      "step": 88
+    },
+    {
+      "epoch": 0.050392809116002545,
+      "grad_norm": 0.022543244063854218,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 11.9276,
+      "step": 89
+    },
+    {
+      "epoch": 0.0509590204543846,
+      "grad_norm": 0.027043450623750687,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 11.9276,
+      "step": 90
+    },
+    {
+      "epoch": 0.05152523179276665,
+      "grad_norm": 0.027559487149119377,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 11.9274,
+      "step": 91
+    },
+    {
+      "epoch": 0.052091443131148704,
+      "grad_norm": 0.029342046007514,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 11.9271,
+      "step": 92
+    },
+    {
+      "epoch": 0.05265765446953075,
+      "grad_norm": 0.03043309599161148,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 11.9261,
+      "step": 93
+    },
+    {
+      "epoch": 0.0532238658079128,
+      "grad_norm": 0.032014548778533936,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 11.9264,
+      "step": 94
+    },
+    {
+      "epoch": 0.05379007714629486,
+      "grad_norm": 0.033974312245845795,
+      "learning_rate": 1e-05,
+      "loss": 11.9274,
+      "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": 1563741388800.0,
+  "total_flos": 1980739092480.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null