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:af7f12e628c52c6b91c112ab7bcb0cb36872f6fed26df12b11f4566440abb978
+oid sha256:e18a5b5d30995f2573c6cce347c904923cb56e798e0421c212e47cfe52f2e1cb
 size 313820248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a67fa7ab9fad067107bdd0bc27848ac0a1e1be9dd5eb2b35184a80fa488a1b84
+oid sha256:ccae53a86be71ea8eb0bd904edaceff0ca96f2ea320d85c31dfc7cd1b8ea0c30
 size 159641092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acdb0c1dd3b45248865124647d1dbbb5d6c6d20faffa5e91280b52fe1b419936
+oid sha256:f04e8f18e15fe3c18edf53c30b7bb83f2728fbac8a1bd06b7fa6089f8c060a87
 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": 0.9000408053398132,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08438818565400844,
+  "best_metric": 0.8787677884101868,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16877637130801687,
   "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": 29.754,
       "eval_steps_per_second": 3.757,
       "step": 25
+    },
+    {
+      "epoch": 0.08776371308016878,
+      "grad_norm": 0.6180962324142456,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.9031,
+      "step": 26
+    },
+    {
+      "epoch": 0.09113924050632911,
+      "grad_norm": 0.5998266935348511,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.9706,
+      "step": 27
+    },
+    {
+      "epoch": 0.09451476793248945,
+      "grad_norm": 0.5918096899986267,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.8448,
+      "step": 28
+    },
+    {
+      "epoch": 0.09789029535864979,
+      "grad_norm": 0.5581284761428833,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.8772,
+      "step": 29
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 0.5750042796134949,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.8812,
+      "step": 30
+    },
+    {
+      "epoch": 0.10464135021097046,
+      "grad_norm": 0.5918043851852417,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.8839,
+      "step": 31
+    },
+    {
+      "epoch": 0.1080168776371308,
+      "grad_norm": 0.589953601360321,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8633,
+      "step": 32
+    },
+    {
+      "epoch": 0.11139240506329114,
+      "grad_norm": 0.6130343079566956,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.9368,
+      "step": 33
+    },
+    {
+      "epoch": 0.11476793248945148,
+      "grad_norm": 0.5803126096725464,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.8662,
+      "step": 34
+    },
+    {
+      "epoch": 0.11814345991561181,
+      "grad_norm": 0.5708263516426086,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8669,
+      "step": 35
+    },
+    {
+      "epoch": 0.12151898734177215,
+      "grad_norm": 0.578863263130188,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.8797,
+      "step": 36
+    },
+    {
+      "epoch": 0.1248945147679325,
+      "grad_norm": 0.5792142748832703,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.8665,
+      "step": 37
+    },
+    {
+      "epoch": 0.12827004219409283,
+      "grad_norm": 0.6031744480133057,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.895,
+      "step": 38
+    },
+    {
+      "epoch": 0.13164556962025317,
+      "grad_norm": 0.6153518557548523,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.911,
+      "step": 39
+    },
+    {
+      "epoch": 0.1350210970464135,
+      "grad_norm": 0.6126015186309814,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.8387,
+      "step": 40
+    },
+    {
+      "epoch": 0.13839662447257384,
+      "grad_norm": 0.5898735523223877,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8764,
+      "step": 41
+    },
+    {
+      "epoch": 0.14177215189873418,
+      "grad_norm": 0.5841656923294067,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.86,
+      "step": 42
+    },
+    {
+      "epoch": 0.1451476793248945,
+      "grad_norm": 0.6128556728363037,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.8682,
+      "step": 43
+    },
+    {
+      "epoch": 0.14852320675105485,
+      "grad_norm": 0.6161452531814575,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.8521,
+      "step": 44
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 0.6541045308113098,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8808,
+      "step": 45
+    },
+    {
+      "epoch": 0.15527426160337554,
+      "grad_norm": 0.6270753741264343,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9077,
+      "step": 46
+    },
+    {
+      "epoch": 0.15864978902953586,
+      "grad_norm": 0.6266160607337952,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.8956,
+      "step": 47
+    },
+    {
+      "epoch": 0.1620253164556962,
+      "grad_norm": 0.6659855246543884,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.9096,
+      "step": 48
+    },
+    {
+      "epoch": 0.16540084388185655,
+      "grad_norm": 0.6978780031204224,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.9074,
+      "step": 49
+    },
+    {
+      "epoch": 0.16877637130801687,
+      "grad_norm": 0.8016338348388672,
+      "learning_rate": 0.0,
+      "loss": 0.9513,
+      "step": 50
+    },
+    {
+      "epoch": 0.16877637130801687,
+      "eval_loss": 0.8787677884101868,
+      "eval_runtime": 16.923,
+      "eval_samples_per_second": 29.486,
+      "eval_steps_per_second": 3.723,
+      "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": 1.01269389705216e+16,
+  "total_flos": 1.9646261602811904e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null