Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efeb72471214f33f06bc2eac66d20a16bf2d646fa5b07b2140a6a46410eac275
+oid sha256:92793f9f091226be518b77d8487a80b1675ecd76c46f67d28bfb7df49209a4cd
 size 406863720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d036bc1eab5312290eb6830361f2457d3add4d5e70613aa107f3671d0f54d47
+oid sha256:6587a2c71480de48d1fe5d86ee338977784cfe90e20aacbd399528d20916fb49
 size 207013892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf9c9b50b3820abb369b5d2a412d699312c3669f06d09541832a89187b6ad1a
+oid sha256:d582d457d208e41de9ebb4b08cb1cea126766e47df048b8aea32ac6f818ce51f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
+oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.004274221137166023,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.3436426116838488,
+  "best_metric": 0.0029016202315688133,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.5154639175257731,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -262,6 +262,133 @@
       "eval_samples_per_second": 20.886,
       "eval_steps_per_second": 5.243,
       "step": 100
+    },
+    {
+      "epoch": 0.35051546391752575,
+      "grad_norm": 0.0898192897439003,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 0.0232,
+      "step": 102
+    },
+    {
+      "epoch": 0.36082474226804123,
+      "grad_norm": 0.005253229755908251,
+      "learning_rate": 5e-05,
+      "loss": 0.0047,
+      "step": 105
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 0.01150997169315815,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 0.0018,
+      "step": 108
+    },
+    {
+      "epoch": 0.38144329896907214,
+      "grad_norm": 0.014451125636696815,
+      "learning_rate": 4.504772348747687e-05,
+      "loss": 0.0013,
+      "step": 111
+    },
+    {
+      "epoch": 0.3917525773195876,
+      "grad_norm": 0.03036060929298401,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 0.0025,
+      "step": 114
+    },
+    {
+      "epoch": 0.4020618556701031,
+      "grad_norm": 0.056347545236349106,
+      "learning_rate": 4.0144148627425993e-05,
+      "loss": 0.0014,
+      "step": 117
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 0.02666492946445942,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.0009,
+      "step": 120
+    },
+    {
+      "epoch": 0.422680412371134,
+      "grad_norm": 0.003874163143336773,
+      "learning_rate": 3.533749813077677e-05,
+      "loss": 0.0005,
+      "step": 123
+    },
+    {
+      "epoch": 0.4329896907216495,
+      "grad_norm": 0.09130533039569855,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 0.0009,
+      "step": 126
+    },
+    {
+      "epoch": 0.44329896907216493,
+      "grad_norm": 0.05246276408433914,
+      "learning_rate": 3.0675041535377405e-05,
+      "loss": 0.0012,
+      "step": 129
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 0.029519734904170036,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 0.0004,
+      "step": 132
+    },
+    {
+      "epoch": 0.4639175257731959,
+      "grad_norm": 0.006854426581412554,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 0.0002,
+      "step": 135
+    },
+    {
+      "epoch": 0.4742268041237113,
+      "grad_norm": 0.09128715097904205,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 0.0013,
+      "step": 138
+    },
+    {
+      "epoch": 0.4845360824742268,
+      "grad_norm": 0.2408163845539093,
+      "learning_rate": 2.196424713241637e-05,
+      "loss": 0.001,
+      "step": 141
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 0.006359494291245937,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 0.0006,
+      "step": 144
+    },
+    {
+      "epoch": 0.5051546391752577,
+      "grad_norm": 0.05870181322097778,
+      "learning_rate": 1.800157297483417e-05,
+      "loss": 0.0007,
+      "step": 147
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 0.572841227054596,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 0.0114,
+      "step": 150
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "eval_loss": 0.0029016202315688133,
+      "eval_runtime": 23.4605,
+      "eval_samples_per_second": 20.886,
+      "eval_steps_per_second": 5.243,
+      "step": 150
     }
   ],
   "logging_steps": 3,
@@ -290,7 +417,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.189988467802112e+16,
+  "total_flos": 1.0759725130973184e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null