Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed47462082a9c9d564f1245e88381edd4919d1c6d927c0a9baa65067dc20478
+oid sha256:d7c7f59d1d0bd853fc30c0d22c6711fa2f6d74d371705f1cc176c9d46f5a7151
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dce2a7c169df44a13155ff92b8c8df0dda9517731e76a254bee2e59ac6ae653
+oid sha256:0c2928577faf9f420c7fd6d3d74c9eec453042ab5c64f233e5f0e06f32b55256
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e51a2209d1739c364384d0bc4e94871f9dbec8f5f6e8abed3de2c7bf755ea5
+oid sha256:16c26aca448a242d5bf2fabc2154114043b520f3da37396f4bb9075805b13b9b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f9eefb79e5a651e4979588997923d1fc997984394f03e9fb61aca38c6bee05
+oid sha256:e6da36b358afefa2fe6fe8e3889efc77dfb89ac577ed7bb55c631123a9ebe149
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.005722765810787678,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.040453074433656956,
+  "best_metric": 0.005342242307960987,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.06067961165048544,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 18.013,
       "eval_steps_per_second": 4.521,
       "step": 100
+    },
+    {
+      "epoch": 0.04449838187702265,
+      "grad_norm": 0.04571974277496338,
+      "learning_rate": 5.05e-06,
+      "loss": 0.0002,
+      "step": 110
+    },
+    {
+      "epoch": 0.04854368932038835,
+      "grad_norm": 0.01307100709527731,
+      "learning_rate": 4.488888888888889e-06,
+      "loss": 0.0007,
+      "step": 120
+    },
+    {
+      "epoch": 0.052588996763754045,
+      "grad_norm": 0.43846479058265686,
+      "learning_rate": 3.927777777777778e-06,
+      "loss": 0.0027,
+      "step": 130
+    },
+    {
+      "epoch": 0.05663430420711974,
+      "grad_norm": 0.002617649268358946,
+      "learning_rate": 3.3666666666666665e-06,
+      "loss": 0.0006,
+      "step": 140
+    },
+    {
+      "epoch": 0.06067961165048544,
+      "grad_norm": 1.0591951608657837,
+      "learning_rate": 2.8055555555555555e-06,
+      "loss": 0.0014,
+      "step": 150
+    },
+    {
+      "epoch": 0.06067961165048544,
+      "eval_loss": 0.005342242307960987,
+      "eval_runtime": 43.2869,
+      "eval_samples_per_second": 18.042,
+      "eval_steps_per_second": 4.528,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.856747589749965e+16,
+  "total_flos": 4.270979069824205e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null