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:b3551c511fe4e115364f91624f9df27936a75936b927e1f0b43c7eab752eb505
+oid sha256:ace085f8f6625f50f53f36ba9765a90df57a02e88436cd15cf77fa816cd6f69b
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3fcd647f0dba5ee358025bcec9eccfe683200f3da3062522a142d25a5448ba
+oid sha256:90e6974fb9dfb036d780944429e29659b04dbcca5d478ccd2ce65ad1fb967ddc
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf8adeadb7ebae27dfc29f6b1d8540e1dff86b5f26230765000382f0016077a8
+oid sha256:ef36da14d0d1018f2e03493c732872b4966004aab3aa2490c4437730270019d4
 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": 0.9847307801246643,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04642525533890436,
+  "best_metric": 0.9741932153701782,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09285051067780872,
   "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": 26.343,
       "eval_steps_per_second": 3.311,
       "step": 25
+    },
+    {
+      "epoch": 0.04828226555246054,
+      "grad_norm": 0.31770119071006775,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.033,
+      "step": 26
+    },
+    {
+      "epoch": 0.05013927576601671,
+      "grad_norm": 0.3336591422557831,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.9795,
+      "step": 27
+    },
+    {
+      "epoch": 0.051996285979572884,
+      "grad_norm": 0.33222416043281555,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.0338,
+      "step": 28
+    },
+    {
+      "epoch": 0.05385329619312906,
+      "grad_norm": 0.3766303062438965,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.924,
+      "step": 29
+    },
+    {
+      "epoch": 0.055710306406685235,
+      "grad_norm": 0.38656023144721985,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.0457,
+      "step": 30
+    },
+    {
+      "epoch": 0.057567316620241414,
+      "grad_norm": 0.33840376138687134,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.0402,
+      "step": 31
+    },
+    {
+      "epoch": 0.059424326833797586,
+      "grad_norm": 0.3422689437866211,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8613,
+      "step": 32
+    },
+    {
+      "epoch": 0.06128133704735376,
+      "grad_norm": 0.37541311979293823,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.0384,
+      "step": 33
+    },
+    {
+      "epoch": 0.06313834726090993,
+      "grad_norm": 0.35279935598373413,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.0677,
+      "step": 34
+    },
+    {
+      "epoch": 0.06499535747446611,
+      "grad_norm": 0.3602738082408905,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1696,
+      "step": 35
+    },
+    {
+      "epoch": 0.06685236768802229,
+      "grad_norm": 0.38732782006263733,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.1272,
+      "step": 36
+    },
+    {
+      "epoch": 0.06870937790157845,
+      "grad_norm": 0.40577706694602966,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.9577,
+      "step": 37
+    },
+    {
+      "epoch": 0.07056638811513463,
+      "grad_norm": 0.3912973403930664,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.0817,
+      "step": 38
+    },
+    {
+      "epoch": 0.07242339832869081,
+      "grad_norm": 0.39627373218536377,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.9677,
+      "step": 39
+    },
+    {
+      "epoch": 0.07428040854224698,
+      "grad_norm": 0.4169067144393921,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.1588,
+      "step": 40
+    },
+    {
+      "epoch": 0.07613741875580315,
+      "grad_norm": 0.4882132411003113,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0261,
+      "step": 41
+    },
+    {
+      "epoch": 0.07799442896935933,
+      "grad_norm": 0.3861491084098816,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9622,
+      "step": 42
+    },
+    {
+      "epoch": 0.07985143918291551,
+      "grad_norm": 0.4414755403995514,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.1227,
+      "step": 43
+    },
+    {
+      "epoch": 0.08170844939647168,
+      "grad_norm": 0.40376952290534973,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.9981,
+      "step": 44
+    },
+    {
+      "epoch": 0.08356545961002786,
+      "grad_norm": 0.4256540834903717,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.9615,
+      "step": 45
+    },
+    {
+      "epoch": 0.08542246982358404,
+      "grad_norm": 0.40966448187828064,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.1133,
+      "step": 46
+    },
+    {
+      "epoch": 0.0872794800371402,
+      "grad_norm": 0.47860437631607056,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.9517,
+      "step": 47
+    },
+    {
+      "epoch": 0.08913649025069638,
+      "grad_norm": 0.4424186646938324,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.0732,
+      "step": 48
+    },
+    {
+      "epoch": 0.09099350046425256,
+      "grad_norm": 0.5190861225128174,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.9601,
+      "step": 49
+    },
+    {
+      "epoch": 0.09285051067780872,
+      "grad_norm": 0.6566285490989685,
+      "learning_rate": 0.0,
+      "loss": 0.8175,
+      "step": 50
+    },
+    {
+      "epoch": 0.09285051067780872,
+      "eval_loss": 0.9741932153701782,
+      "eval_runtime": 33.8942,
+      "eval_samples_per_second": 26.76,
+      "eval_steps_per_second": 3.363,
+      "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": 1.884002508079104e+16,
+  "total_flos": 3.661363364757504e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null