Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cff14d010caad12d4df329ed30af9f6db8daf20e04615f7df6cf37a1441083
+oid sha256:61ac2c149015501cde8cc110f2a5bab5d22c143fdb4b510c0747ba987cf2e7f7
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cbae21d6deb7f4c3735d7922115edfe0a648f0913838facf5102b61869392d0
+oid sha256:1016cfe7c37385f0a7d7abe0d1c99ae41a2644607dd95fc15b4ce4fbe89df0f7
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e341f244f7b29f6b2dfa2e84bea200f2bb0a932b64c0fc42a38c495bacea2bc1
+oid sha256:e96ab202b9b1794de1e20d736a0c7fe81306f397f74ab866394f6ff50c898138
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6936973333358765,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004052028040034037,
+  "best_metric": 1.5977141857147217,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.008104056080068074,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 13.747,
       "eval_steps_per_second": 1.718,
       "step": 25
+    },
+    {
+      "epoch": 0.004214109161635398,
+      "grad_norm": 5.783700942993164,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 6.5527,
+      "step": 26
+    },
+    {
+      "epoch": 0.00437619028323676,
+      "grad_norm": 5.581294536590576,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 6.161,
+      "step": 27
+    },
+    {
+      "epoch": 0.004538271404838121,
+      "grad_norm": 5.728160858154297,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 6.3117,
+      "step": 28
+    },
+    {
+      "epoch": 0.004700352526439483,
+      "grad_norm": 5.748680114746094,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 6.4574,
+      "step": 29
+    },
+    {
+      "epoch": 0.004862433648040844,
+      "grad_norm": 5.648220539093018,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 6.215,
+      "step": 30
+    },
+    {
+      "epoch": 0.005024514769642206,
+      "grad_norm": 5.6319379806518555,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 5.9622,
+      "step": 31
+    },
+    {
+      "epoch": 0.005186595891243567,
+      "grad_norm": 5.8718953132629395,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 6.2086,
+      "step": 32
+    },
+    {
+      "epoch": 0.005348677012844929,
+      "grad_norm": 6.098597049713135,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 6.38,
+      "step": 33
+    },
+    {
+      "epoch": 0.00551075813444629,
+      "grad_norm": 6.240828990936279,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 6.3073,
+      "step": 34
+    },
+    {
+      "epoch": 0.005672839256047652,
+      "grad_norm": 6.659487247467041,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.5308,
+      "step": 35
+    },
+    {
+      "epoch": 0.005834920377649013,
+      "grad_norm": 6.27744197845459,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 6.113,
+      "step": 36
+    },
+    {
+      "epoch": 0.005997001499250375,
+      "grad_norm": 6.688141345977783,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 6.5809,
+      "step": 37
+    },
+    {
+      "epoch": 0.006159082620851736,
+      "grad_norm": 7.0126447677612305,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 6.6365,
+      "step": 38
+    },
+    {
+      "epoch": 0.006321163742453098,
+      "grad_norm": 7.171256065368652,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 6.8393,
+      "step": 39
+    },
+    {
+      "epoch": 0.006483244864054459,
+      "grad_norm": 8.205148696899414,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 7.0387,
+      "step": 40
+    },
+    {
+      "epoch": 0.0066453259856558205,
+      "grad_norm": 8.000205993652344,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.1483,
+      "step": 41
+    },
+    {
+      "epoch": 0.006807407107257182,
+      "grad_norm": 7.7371697425842285,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 6.6281,
+      "step": 42
+    },
+    {
+      "epoch": 0.0069694882288585435,
+      "grad_norm": 8.671666145324707,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 7.1924,
+      "step": 43
+    },
+    {
+      "epoch": 0.007131569350459905,
+      "grad_norm": 9.656037330627441,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 6.8932,
+      "step": 44
+    },
+    {
+      "epoch": 0.007293650472061266,
+      "grad_norm": 9.278881072998047,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 6.8363,
+      "step": 45
+    },
+    {
+      "epoch": 0.007455731593662628,
+      "grad_norm": 10.156712532043457,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 7.2396,
+      "step": 46
+    },
+    {
+      "epoch": 0.007617812715263989,
+      "grad_norm": 11.086377143859863,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 7.0737,
+      "step": 47
+    },
+    {
+      "epoch": 0.007779893836865351,
+      "grad_norm": 12.269014358520508,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 7.1526,
+      "step": 48
+    },
+    {
+      "epoch": 0.007941974958466713,
+      "grad_norm": 14.667993545532227,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 7.5643,
+      "step": 49
+    },
+    {
+      "epoch": 0.008104056080068074,
+      "grad_norm": 21.117507934570312,
+      "learning_rate": 0.0,
+      "loss": 6.5986,
+      "step": 50
+    },
+    {
+      "epoch": 0.008104056080068074,
+      "eval_loss": 1.5977141857147217,
+      "eval_runtime": 756.8752,
+      "eval_samples_per_second": 13.73,
+      "eval_steps_per_second": 1.716,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.60924825255936e+16,
+  "total_flos": 6.857571679862784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null