Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426879a261b11294a00136a2887d74ff83ba5a97e8c19a010bb761823e7d61f0
+oid sha256:44b5a90cbae015dfc7be5202391501d2928f4f0767384038e1df885dbf47ed45
 size 435773944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f73f5a75697924b84165d85237b25c1c8245529b515fd2b94355c72f59a7913
+oid sha256:eb8d9363a7dfcef3b000a69e27d77c3b61ff00273a6f2f166771555b98f88230
 size 222034900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc0522d3ce3293fdc3daf1f9bf340216e9b0d29b746ba36bf3cfda15e2b6aa09
+oid sha256:f58a55fcf967a46936d11fd0124d1ff2bd8c83df24764f5a640a993eb06eec71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bb1aa192c7f9c0516bbbf45e738ece50573944baeb2415a4a135a1ac346045
+oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3171169757843018,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.01224889759921607,
+  "best_metric": 1.2731058597564697,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.018373346398824104,
   "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": 10.4,
       "eval_steps_per_second": 2.602,
       "step": 100
+    },
+    {
+      "epoch": 0.013473787359137677,
+      "grad_norm": 0.7750642895698547,
+      "learning_rate": 5.095e-06,
+      "loss": 0.9114,
+      "step": 110
+    },
+    {
+      "epoch": 0.014698677119059285,
+      "grad_norm": 1.0988212823867798,
+      "learning_rate": 4.5288888888888885e-06,
+      "loss": 1.0442,
+      "step": 120
+    },
+    {
+      "epoch": 0.01592356687898089,
+      "grad_norm": 1.7154313325881958,
+      "learning_rate": 3.9627777777777784e-06,
+      "loss": 1.0348,
+      "step": 130
+    },
+    {
+      "epoch": 0.0171484566389025,
+      "grad_norm": 3.957415819168091,
+      "learning_rate": 3.3966666666666666e-06,
+      "loss": 1.4493,
+      "step": 140
+    },
+    {
+      "epoch": 0.018373346398824104,
+      "grad_norm": 11.051023483276367,
+      "learning_rate": 2.830555555555556e-06,
+      "loss": 1.9913,
+      "step": 150
+    },
+    {
+      "epoch": 0.018373346398824104,
+      "eval_loss": 1.2731058597564697,
+      "eval_runtime": 247.9535,
+      "eval_samples_per_second": 10.397,
+      "eval_steps_per_second": 2.601,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2303723782864896e+16,
+  "total_flos": 4.82956662496297e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null