Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3e2489a0e02b26295f1fb31d411912ae347f7c08847bc81d39ceb4915f7e10
+oid sha256:71163eba497522ab3bb9fb67bcc00b0fc3154d305010741c7d4946bc686cead1
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6dadc653d945a059dca874ae81f7e8072acc0e9331dc88fa6677dba64e9f91d
+oid sha256:e3759ac112158705c8871f7a972fc37d1cd41e812ca911d2965295102cb92414
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789256e4db352b105989c82fcd8d9ad9ebeb7df942172b984edc061657aa1b9e
+oid sha256:58068390239d663bb7e24914ab842941b13473a1f0cb264a2f92451905658929
 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": 1.5552066564559937,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05847953216374269,
+  "best_metric": 1.5078009366989136,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11695906432748537,
   "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": 23.301,
       "eval_steps_per_second": 2.913,
       "step": 25
+    },
+    {
+      "epoch": 0.0608187134502924,
+      "grad_norm": 0.775091290473938,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.7077,
+      "step": 26
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 0.8018562197685242,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.6566,
+      "step": 27
+    },
+    {
+      "epoch": 0.06549707602339182,
+      "grad_norm": 0.9043634533882141,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.7128,
+      "step": 28
+    },
+    {
+      "epoch": 0.06783625730994151,
+      "grad_norm": 0.7843608856201172,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4492,
+      "step": 29
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.8838165402412415,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.278,
+      "step": 30
+    },
+    {
+      "epoch": 0.07251461988304093,
+      "grad_norm": 0.9731401801109314,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.5392,
+      "step": 31
+    },
+    {
+      "epoch": 0.07485380116959064,
+      "grad_norm": 0.9145104885101318,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.488,
+      "step": 32
+    },
+    {
+      "epoch": 0.07719298245614035,
+      "grad_norm": 1.04607355594635,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.416,
+      "step": 33
+    },
+    {
+      "epoch": 0.07953216374269007,
+      "grad_norm": 1.0921167135238647,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.4416,
+      "step": 34
+    },
+    {
+      "epoch": 0.08187134502923976,
+      "grad_norm": 1.0760698318481445,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3297,
+      "step": 35
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 1.0848755836486816,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.2409,
+      "step": 36
+    },
+    {
+      "epoch": 0.08654970760233918,
+      "grad_norm": 1.0526748895645142,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.255,
+      "step": 37
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.0006829500198364,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.278,
+      "step": 38
+    },
+    {
+      "epoch": 0.0912280701754386,
+      "grad_norm": 1.306719183921814,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.4427,
+      "step": 39
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "grad_norm": 1.3482352495193481,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.5202,
+      "step": 40
+    },
+    {
+      "epoch": 0.09590643274853801,
+      "grad_norm": 1.474596381187439,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3921,
+      "step": 41
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 1.5520974397659302,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4067,
+      "step": 42
+    },
+    {
+      "epoch": 0.10058479532163743,
+      "grad_norm": 1.6975865364074707,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.5062,
+      "step": 43
+    },
+    {
+      "epoch": 0.10292397660818714,
+      "grad_norm": 2.409618616104126,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4462,
+      "step": 44
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.2302913665771484,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.256,
+      "step": 45
+    },
+    {
+      "epoch": 0.10760233918128655,
+      "grad_norm": 4.018095016479492,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3955,
+      "step": 46
+    },
+    {
+      "epoch": 0.10994152046783626,
+      "grad_norm": 3.443303346633911,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.7946,
+      "step": 47
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 3.7554218769073486,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.9503,
+      "step": 48
+    },
+    {
+      "epoch": 0.11461988304093568,
+      "grad_norm": 7.074597358703613,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.0189,
+      "step": 49
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "grad_norm": 10.611915588378906,
+      "learning_rate": 0.0,
+      "loss": 3.3674,
+      "step": 50
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "eval_loss": 1.5078009366989136,
+      "eval_runtime": 30.6067,
+      "eval_samples_per_second": 23.524,
+      "eval_steps_per_second": 2.941,
+      "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": 2.281626787853107e+16,
+  "total_flos": 4.167268761285427e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null