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:df45b410f992cbf73ad382fe396743c59a79bd2de9b6d9d658db8cb37c640b6e
+oid sha256:708c7a44f3fec906e39abdf6c83bcd2e8505a9a1d36f950547b10c2bf2eedb00
 size 478211024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a5ca01073a22eb3195245b387c1b6c33a7751471b7122b6ff52e65d8b5faf6
+oid sha256:04c514f09b4a5d953431067267c96aae3f917e540107ac0f2a671c2773013658
 size 243337876

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6827b214e244873d769b3511a9077fd911b0e01059702f41c2a2be6f3d263aec
+oid sha256:4cafd4b4735ebf56c468e53e27ec0af71c689dcad46f3d73866674866f548322
 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": 1.1481486558914185,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016909029421711193,
+  "best_metric": 1.1276003122329712,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.033818058843422386,
   "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": 39.22,
       "eval_steps_per_second": 4.914,
       "step": 25
+    },
+    {
+      "epoch": 0.01758539059857964,
+      "grad_norm": 1.4838390350341797,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.6324,
+      "step": 26
+    },
+    {
+      "epoch": 0.01826175177544809,
+      "grad_norm": 1.5631728172302246,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 4.7677,
+      "step": 27
+    },
+    {
+      "epoch": 0.018938112952316538,
+      "grad_norm": 1.4975249767303467,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 4.4577,
+      "step": 28
+    },
+    {
+      "epoch": 0.019614474129184985,
+      "grad_norm": 1.5627292394638062,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 4.4784,
+      "step": 29
+    },
+    {
+      "epoch": 0.020290835306053433,
+      "grad_norm": 1.6029400825500488,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.672,
+      "step": 30
+    },
+    {
+      "epoch": 0.02096719648292188,
+      "grad_norm": 1.5164552927017212,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.7107,
+      "step": 31
+    },
+    {
+      "epoch": 0.021643557659790327,
+      "grad_norm": 1.4938106536865234,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.2752,
+      "step": 32
+    },
+    {
+      "epoch": 0.022319918836658775,
+      "grad_norm": 1.6547623872756958,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 4.6671,
+      "step": 33
+    },
+    {
+      "epoch": 0.022996280013527222,
+      "grad_norm": 1.5448929071426392,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.347,
+      "step": 34
+    },
+    {
+      "epoch": 0.023672641190395673,
+      "grad_norm": 1.615652322769165,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.6043,
+      "step": 35
+    },
+    {
+      "epoch": 0.02434900236726412,
+      "grad_norm": 1.6707816123962402,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 4.7418,
+      "step": 36
+    },
+    {
+      "epoch": 0.025025363544132567,
+      "grad_norm": 1.640742301940918,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 4.7379,
+      "step": 37
+    },
+    {
+      "epoch": 0.025701724721001015,
+      "grad_norm": 1.592197299003601,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.6499,
+      "step": 38
+    },
+    {
+      "epoch": 0.026378085897869462,
+      "grad_norm": 1.702347755432129,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.6663,
+      "step": 39
+    },
+    {
+      "epoch": 0.02705444707473791,
+      "grad_norm": 1.5496896505355835,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.4641,
+      "step": 40
+    },
+    {
+      "epoch": 0.027730808251606356,
+      "grad_norm": 1.818640947341919,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.676,
+      "step": 41
+    },
+    {
+      "epoch": 0.028407169428474807,
+      "grad_norm": 1.699539065361023,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 4.515,
+      "step": 42
+    },
+    {
+      "epoch": 0.029083530605343254,
+      "grad_norm": 1.6481209993362427,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.4317,
+      "step": 43
+    },
+    {
+      "epoch": 0.029759891782211702,
+      "grad_norm": 1.679146647453308,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 4.6045,
+      "step": 44
+    },
+    {
+      "epoch": 0.03043625295908015,
+      "grad_norm": 1.7702221870422363,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.5777,
+      "step": 45
+    },
+    {
+      "epoch": 0.031112614135948596,
+      "grad_norm": 1.8951936960220337,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 4.546,
+      "step": 46
+    },
+    {
+      "epoch": 0.03178897531281705,
+      "grad_norm": 1.952268362045288,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 4.6064,
+      "step": 47
+    },
+    {
+      "epoch": 0.03246533648968549,
+      "grad_norm": 1.949053406715393,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 4.4643,
+      "step": 48
+    },
+    {
+      "epoch": 0.03314169766655394,
+      "grad_norm": 2.287039279937744,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.7819,
+      "step": 49
+    },
+    {
+      "epoch": 0.033818058843422386,
+      "grad_norm": 3.5385773181915283,
+      "learning_rate": 0.0,
+      "loss": 5.4656,
+      "step": 50
+    },
+    {
+      "epoch": 0.033818058843422386,
+      "eval_loss": 1.1276003122329712,
+      "eval_runtime": 63.5618,
+      "eval_samples_per_second": 39.174,
+      "eval_steps_per_second": 4.909,
+      "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": 9914505064611840.0,
+  "total_flos": 1.935689084043264e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null