Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ffa2719766e98eb3394258ff1e4f0b39f8d7c7f8ce97a22a4b9ae18c0b8d12
+oid sha256:a4d351d3a8f5ac0f89e0485970314c3b3f28232bda6efad52b1b9d327f90234e
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d1bb9bc7fb7e782fff5a97480723ffc068c8128f36450d1a3eefe0726c6935
+oid sha256:5c0ddcbc5d81b436daaaf2bb3c9968befc3506d00620777be5bcac571cac6c54
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa36ed22fc82118b516b289f129dcd3085f3af84b6bc2f07cb00d4043c9eff7
+oid sha256:e5eb6fa3c42c54eb21887e7eb936066a407d9591b2cd7bada806a85c4a300138
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3386822938919067,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0013101867016049786,
+  "best_metric": 1.3211801052093506,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0026203734032099572,
   "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": 9.759,
       "eval_steps_per_second": 4.88,
       "step": 25
+    },
+    {
+      "epoch": 0.0013625941696691778,
+      "grad_norm": 0.39403942227363586,
+      "learning_rate": 0.0001,
+      "loss": 1.2445,
+      "step": 26
+    },
+    {
+      "epoch": 0.001415001637733377,
+      "grad_norm": 0.43036386370658875,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.2675,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014674091057975762,
+      "grad_norm": 0.36898255348205566,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.2681,
+      "step": 28
+    },
+    {
+      "epoch": 0.0015198165738617754,
+      "grad_norm": 0.48340263962745667,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.1686,
+      "step": 29
+    },
+    {
+      "epoch": 0.0015722240419259745,
+      "grad_norm": 0.413663387298584,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.2895,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016246315099901737,
+      "grad_norm": 0.4055498242378235,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.2696,
+      "step": 31
+    },
+    {
+      "epoch": 0.0016770389780543728,
+      "grad_norm": 0.4815317988395691,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.3778,
+      "step": 32
+    },
+    {
+      "epoch": 0.001729446446118572,
+      "grad_norm": 0.4714352786540985,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.345,
+      "step": 33
+    },
+    {
+      "epoch": 0.001781853914182771,
+      "grad_norm": 0.48492833971977234,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.3,
+      "step": 34
+    },
+    {
+      "epoch": 0.0018342613822469702,
+      "grad_norm": 0.5202695727348328,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.3596,
+      "step": 35
+    },
+    {
+      "epoch": 0.0018866688503111693,
+      "grad_norm": 0.5492162108421326,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.3763,
+      "step": 36
+    },
+    {
+      "epoch": 0.0019390763183753685,
+      "grad_norm": 0.5086742043495178,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.3309,
+      "step": 37
+    },
+    {
+      "epoch": 0.0019914837864395676,
+      "grad_norm": 0.6512495279312134,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.2766,
+      "step": 38
+    },
+    {
+      "epoch": 0.002043891254503767,
+      "grad_norm": 0.5928826332092285,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.2372,
+      "step": 39
+    },
+    {
+      "epoch": 0.002096298722567966,
+      "grad_norm": 0.9627623558044434,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.3238,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021487061906321652,
+      "grad_norm": 1.0270004272460938,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.4212,
+      "step": 41
+    },
+    {
+      "epoch": 0.002201113658696364,
+      "grad_norm": 1.0594191551208496,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.1272,
+      "step": 42
+    },
+    {
+      "epoch": 0.0022535211267605635,
+      "grad_norm": 1.4876549243927002,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 1.3084,
+      "step": 43
+    },
+    {
+      "epoch": 0.0023059285948247624,
+      "grad_norm": 2.034849166870117,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.5273,
+      "step": 44
+    },
+    {
+      "epoch": 0.0023583360628889618,
+      "grad_norm": 1.6223154067993164,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 1.4066,
+      "step": 45
+    },
+    {
+      "epoch": 0.0024107435309531607,
+      "grad_norm": 1.6114851236343384,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.2965,
+      "step": 46
+    },
+    {
+      "epoch": 0.00246315099901736,
+      "grad_norm": 1.6107181310653687,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.4148,
+      "step": 47
+    },
+    {
+      "epoch": 0.002515558467081559,
+      "grad_norm": 1.9817970991134644,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.6692,
+      "step": 48
+    },
+    {
+      "epoch": 0.0025679659351457583,
+      "grad_norm": 5.455220699310303,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.7254,
+      "step": 49
+    },
+    {
+      "epoch": 0.0026203734032099572,
+      "grad_norm": 7.535577297210693,
+      "learning_rate": 0.0,
+      "loss": 2.5626,
+      "step": 50
+    },
+    {
+      "epoch": 0.0026203734032099572,
+      "eval_loss": 1.3211801052093506,
+      "eval_runtime": 823.1773,
+      "eval_samples_per_second": 9.761,
+      "eval_steps_per_second": 4.881,
+      "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": 5146843860172800.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null