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:a599afe33339e8735dc493d1afacba2379a7c7f35d550797bdd54ff4bbd1eb8d
+oid sha256:2e102c30e59bc688fb507b409d6a0d425d9d373cf4b53582a183559d3a2a2ebe
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e763e85a7b6cf7d792e3d6d20c217568faf042da8f819caa4969bee4161148bc
+oid sha256:42b86d905c6ad2edb24e880a9905136f5831748c1d3bb7cfd2d2c72a5ea3b8b5
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7aac90f6eb7e05de326d2903081e82df3f0f85738a7e50455227eeb959f80eb
+oid sha256:d1099f0d3ca301224a793c68dd5db2f7e3f93cb233113e8497c26d866498940e
 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": 0.9290362000465393,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006130831953896143,
+  "best_metric": 0.9062680602073669,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012261663907792287,
   "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": 111.669,
       "eval_steps_per_second": 13.967,
       "step": 25
+    },
+    {
+      "epoch": 0.00637606523205199,
+      "grad_norm": 2.186485767364502,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.698,
+      "step": 26
+    },
+    {
+      "epoch": 0.0066212985102078355,
+      "grad_norm": 1.7273895740509033,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.6792,
+      "step": 27
+    },
+    {
+      "epoch": 0.006866531788363681,
+      "grad_norm": 1.7794185876846313,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.6554,
+      "step": 28
+    },
+    {
+      "epoch": 0.007111765066519527,
+      "grad_norm": 2.5254006385803223,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.6137,
+      "step": 29
+    },
+    {
+      "epoch": 0.0073569983446753725,
+      "grad_norm": 2.629108190536499,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.7987,
+      "step": 30
+    },
+    {
+      "epoch": 0.007602231622831218,
+      "grad_norm": 2.330003261566162,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.7759,
+      "step": 31
+    },
+    {
+      "epoch": 0.007847464900987065,
+      "grad_norm": 1.9561796188354492,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.7232,
+      "step": 32
+    },
+    {
+      "epoch": 0.00809269817914291,
+      "grad_norm": 1.9218026399612427,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.6606,
+      "step": 33
+    },
+    {
+      "epoch": 0.008337931457298756,
+      "grad_norm": 2.328287363052368,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.7222,
+      "step": 34
+    },
+    {
+      "epoch": 0.0085831647354546,
+      "grad_norm": 1.94029700756073,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6779,
+      "step": 35
+    },
+    {
+      "epoch": 0.008828398013610447,
+      "grad_norm": 2.254920721054077,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.8464,
+      "step": 36
+    },
+    {
+      "epoch": 0.009073631291766292,
+      "grad_norm": 2.38248610496521,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.884,
+      "step": 37
+    },
+    {
+      "epoch": 0.009318864569922139,
+      "grad_norm": 2.4375357627868652,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.8099,
+      "step": 38
+    },
+    {
+      "epoch": 0.009564097848077983,
+      "grad_norm": 2.03926157951355,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.7842,
+      "step": 39
+    },
+    {
+      "epoch": 0.00980933112623383,
+      "grad_norm": 2.372565746307373,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.999,
+      "step": 40
+    },
+    {
+      "epoch": 0.010054564404389676,
+      "grad_norm": 2.33776593208313,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9935,
+      "step": 41
+    },
+    {
+      "epoch": 0.010299797682545521,
+      "grad_norm": 2.4385986328125,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.91,
+      "step": 42
+    },
+    {
+      "epoch": 0.010545030960701368,
+      "grad_norm": 2.182403564453125,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.7364,
+      "step": 43
+    },
+    {
+      "epoch": 0.010790264238857213,
+      "grad_norm": 3.0152950286865234,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0816,
+      "step": 44
+    },
+    {
+      "epoch": 0.011035497517013059,
+      "grad_norm": 2.719191312789917,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.9542,
+      "step": 45
+    },
+    {
+      "epoch": 0.011280730795168904,
+      "grad_norm": 2.710448741912842,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.0482,
+      "step": 46
+    },
+    {
+      "epoch": 0.01152596407332475,
+      "grad_norm": 2.3955540657043457,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7571,
+      "step": 47
+    },
+    {
+      "epoch": 0.011771197351480595,
+      "grad_norm": 2.686272382736206,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.7963,
+      "step": 48
+    },
+    {
+      "epoch": 0.012016430629636442,
+      "grad_norm": 2.5789783000946045,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7878,
+      "step": 49
+    },
+    {
+      "epoch": 0.012261663907792287,
+      "grad_norm": 3.467966318130493,
+      "learning_rate": 0.0,
+      "loss": 0.8873,
+      "step": 50
+    },
+    {
+      "epoch": 0.012261663907792287,
+      "eval_loss": 0.9062680602073669,
+      "eval_runtime": 61.3152,
+      "eval_samples_per_second": 112.011,
+      "eval_steps_per_second": 14.01,
+      "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": 995042113093632.0,
+  "total_flos": 1961102417068032.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null