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:c24cfdac0642280024d08fee535ea2ed3fc0371ea2a35a181eca4013cb2bd3ab
+oid sha256:2ba6cd343730e3c5e1a149865096c31ac20cd2f323e1bd178af029fc6810232d
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ae16ea8b04c504c9c68fb7d2d0fea1d31cc29c00089176ea35abf74ff88dee
+oid sha256:f605717d77142f10bc76b183167207cd5a0fb5822c6f97197a81cbff0626afed
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa9e3011ae95dbb07328cfa992efd78c7dd321fa4004dcd5616c190a230417cf
+oid sha256:7a4e273b41c46ae363b3d5f5d2ef0a5518ca338ea410ed93a3faeb1a9d2062de
 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": 1.3773066997528076,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.002789166875854182,
+  "best_metric": 1.336289644241333,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.0041837503137812735,
   "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": 27.811,
       "eval_steps_per_second": 6.954,
       "step": 100
+    },
+    {
+      "epoch": 0.0030680835634396006,
+      "grad_norm": 2.741830587387085,
+      "learning_rate": 5.05e-06,
+      "loss": 1.6088,
+      "step": 110
+    },
+    {
+      "epoch": 0.0033470002510250186,
+      "grad_norm": 2.751880407333374,
+      "learning_rate": 4.488888888888889e-06,
+      "loss": 1.2966,
+      "step": 120
+    },
+    {
+      "epoch": 0.003625916938610437,
+      "grad_norm": 3.4367833137512207,
+      "learning_rate": 3.927777777777778e-06,
+      "loss": 1.349,
+      "step": 130
+    },
+    {
+      "epoch": 0.0039048336261958555,
+      "grad_norm": 3.5134706497192383,
+      "learning_rate": 3.3666666666666665e-06,
+      "loss": 1.302,
+      "step": 140
+    },
+    {
+      "epoch": 0.0041837503137812735,
+      "grad_norm": 5.4509100914001465,
+      "learning_rate": 2.8055555555555555e-06,
+      "loss": 1.2418,
+      "step": 150
+    },
+    {
+      "epoch": 0.0041837503137812735,
+      "eval_loss": 1.336289644241333,
+      "eval_runtime": 539.6746,
+      "eval_samples_per_second": 27.974,
+      "eval_steps_per_second": 6.995,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.262770368118784e+16,
+  "total_flos": 3.394155552178176e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null