Training in progress, step 169, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19c1114cf9de6f90bb1940716efc651b9605c6686d762ccf3b799f2811954900
+oid sha256:f22aaec3cac7dbfc15d4391d11c107f762520e2a37f8f5c2d98b942859cfa265
 size 34456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6288c9042eef800d7a76ae542ddc00508d162489808b760e57c411c54be14bbb
+oid sha256:507707f766c154dbb2ac88fd1a5769dacf95d66b6840c7348b9c16e3b5637d22
 size 73222

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d3d40ed55247e1860a6d2a1fe1407fda345f4df777e8940c311c2a22735bb4
+oid sha256:5f2e708e3d8d8f020284c0e4a1ec7c83f8e6b27b3fb83632b95fc16e110a981b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6d06d8784fc6f54a8110cd39f154f94ee6f23e5166c1919457b2653a531f69
+oid sha256:72b7ae54645fe0d156a539f19196af82ec47c612b8d4b4a4f763b2303308dc68
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.8875739644970414,
+  "epoch": 1.0,
   "eval_steps": 150,
-  "global_step": 150,
+  "global_step": 169,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1073,6 +1073,139 @@
       "eval_samples_per_second": 199.677,
       "eval_steps_per_second": 50.445,
       "step": 150
+    },
+    {
+      "epoch": 0.893491124260355,
+      "grad_norm": 0.0005075408262200654,
+      "learning_rate": 3.557894822359864e-06,
+      "loss": 46.0,
+      "step": 151
+    },
+    {
+      "epoch": 0.8994082840236687,
+      "grad_norm": 0.00039445646689273417,
+      "learning_rate": 3.1776812947865385e-06,
+      "loss": 46.0,
+      "step": 152
+    },
+    {
+      "epoch": 0.9053254437869822,
+      "grad_norm": 0.00035393863799981773,
+      "learning_rate": 2.8182821739164534e-06,
+      "loss": 46.0,
+      "step": 153
+    },
+    {
+      "epoch": 0.9112426035502958,
+      "grad_norm": 0.0005202327738516033,
+      "learning_rate": 2.4798572271356846e-06,
+      "loss": 46.0,
+      "step": 154
+    },
+    {
+      "epoch": 0.9171597633136095,
+      "grad_norm": 0.0002673721464816481,
+      "learning_rate": 2.1625568979651014e-06,
+      "loss": 46.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.0005175816477276385,
+      "learning_rate": 1.8665222391821169e-06,
+      "loss": 46.0,
+      "step": 156
+    },
+    {
+      "epoch": 0.9289940828402367,
+      "grad_norm": 0.0004950053407810628,
+      "learning_rate": 1.5918848501170647e-06,
+      "loss": 46.0,
+      "step": 157
+    },
+    {
+      "epoch": 0.9349112426035503,
+      "grad_norm": 0.0003163626533932984,
+      "learning_rate": 1.338766818151982e-06,
+      "loss": 46.0,
+      "step": 158
+    },
+    {
+      "epoch": 0.9408284023668639,
+      "grad_norm": 0.0004616921942215413,
+      "learning_rate": 1.1072806644478739e-06,
+      "loss": 46.0,
+      "step": 159
+    },
+    {
+      "epoch": 0.9467455621301775,
+      "grad_norm": 0.0003856797411572188,
+      "learning_rate": 8.975292939244928e-07,
+      "loss": 46.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.9526627218934911,
+      "grad_norm": 0.0004804205091204494,
+      "learning_rate": 7.096059495149854e-07,
+      "loss": 46.0,
+      "step": 161
+    },
+    {
+      "epoch": 0.9585798816568047,
+      "grad_norm": 0.0006341671105474234,
+      "learning_rate": 5.435941707156389e-07,
+      "loss": 46.0,
+      "step": 162
+    },
+    {
+      "epoch": 0.9644970414201184,
+      "grad_norm": 0.0005707453237846494,
+      "learning_rate": 3.9956775644920395e-07,
+      "loss": 46.0,
+      "step": 163
+    },
+    {
+      "epoch": 0.9704142011834319,
+      "grad_norm": 0.0003669565194286406,
+      "learning_rate": 2.77590732258326e-07,
+      "loss": 46.0,
+      "step": 164
+    },
+    {
+      "epoch": 0.9763313609467456,
+      "grad_norm": 0.0006033536046743393,
+      "learning_rate": 1.7771732184357904e-07,
+      "loss": 46.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.9822485207100592,
+      "grad_norm": 0.00046527519589290023,
+      "learning_rate": 9.999192295886972e-08,
+      "loss": 46.0,
+      "step": 166
+    },
+    {
+      "epoch": 0.9881656804733728,
+      "grad_norm": 0.0005233949050307274,
+      "learning_rate": 4.4449087674847125e-08,
+      "loss": 46.0,
+      "step": 167
+    },
+    {
+      "epoch": 0.9940828402366864,
+      "grad_norm": 0.0007509227143600583,
+      "learning_rate": 1.111350701909486e-08,
+      "loss": 46.0,
+      "step": 168
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.00042899660184048116,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 169
     }
   ],
   "logging_steps": 1,
@@ -1096,12 +1229,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 23656569176064.0,
+  "total_flos": 26545806065664.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null