Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22745bde08c2e70b8a2dd738cc1e12154678f613ecfae7f1b17425105dadb254
+oid sha256:2491b19641a83c3100dcc61af3163180a2db53dcce4292c7d419c609d34bb70d
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33b6558e6ad6a584d482d8509de085b96d37856f4ec6a84ccd65e5aaa2910be5
+oid sha256:7bcd08c8b1fdd8e62a7a60ced12d81cb85eda7c836d0829e012a50ba84954714
 size 323290986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a299351b5290b905b6fb731c66a8c6a0a2d2512bf038534bf109e69dc6fd20d
+oid sha256:8b37e212cb6da740e340e977b7b5d15111182fa3aa539864bb4ca6194ace130a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f38702cc21ff53949f9e512e4811bece0110e662b9da53c326be7486b071e884
+oid sha256:13dbd38dba64fee7f6ec1aa76abeb92baf0516af93150f4708883c47690b5ff0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968fae3b27d21dff64ad0dbb9d1fcd4af1546d759f8a1b0e5b7dd60241fa887e
+oid sha256:96a96c263025f52bb9db1918a2bd42b418835444bb648d579c1bad2505b93853
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c300c4f0c4958c92e4cfeca6708ce33f465c9e503411bd540cc8962eb0a3d38b
+oid sha256:cd414757b26e9d00e010628cdb883559d191efd185c38d1ed5e245585c97034f
 size 15024

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": 0.4461486041545868,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1388888888888889,
+  "best_metric": 0.41205424070358276,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2777777777777778,
   "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": 18.208,
       "eval_steps_per_second": 2.283,
       "step": 25
+    },
+    {
+      "epoch": 0.14444444444444443,
+      "grad_norm": 1.2631767988204956,
+      "learning_rate": 0.0001,
+      "loss": 0.453,
+      "step": 26
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.6569949388504028,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.391,
+      "step": 27
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.5892360806465149,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.391,
+      "step": 28
+    },
+    {
+      "epoch": 0.16111111111111112,
+      "grad_norm": 0.4772840142250061,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.3825,
+      "step": 29
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.49844616651535034,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.3935,
+      "step": 30
+    },
+    {
+      "epoch": 0.17222222222222222,
+      "grad_norm": 0.5804672241210938,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.3904,
+      "step": 31
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6754660606384277,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.455,
+      "step": 32
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.7096507549285889,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.3855,
+      "step": 33
+    },
+    {
+      "epoch": 0.18888888888888888,
+      "grad_norm": 0.841553270816803,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5186,
+      "step": 34
+    },
+    {
+      "epoch": 0.19444444444444445,
+      "grad_norm": 0.8675558567047119,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.5228,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9037607908248901,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.447,
+      "step": 36
+    },
+    {
+      "epoch": 0.20555555555555555,
+      "grad_norm": 0.8918576836585999,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.5691,
+      "step": 37
+    },
+    {
+      "epoch": 0.2111111111111111,
+      "grad_norm": 0.5170290470123291,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.3631,
+      "step": 38
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.4087221622467041,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.3581,
+      "step": 39
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.4844251871109009,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.3853,
+      "step": 40
+    },
+    {
+      "epoch": 0.22777777777777777,
+      "grad_norm": 0.4298355281352997,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.3488,
+      "step": 41
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.4732954800128937,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.2975,
+      "step": 42
+    },
+    {
+      "epoch": 0.2388888888888889,
+      "grad_norm": 0.5626371502876282,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.4026,
+      "step": 43
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 0.5444206595420837,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.3887,
+      "step": 44
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.5694227814674377,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.3869,
+      "step": 45
+    },
+    {
+      "epoch": 0.25555555555555554,
+      "grad_norm": 0.5591428875923157,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.3549,
+      "step": 46
+    },
+    {
+      "epoch": 0.2611111111111111,
+      "grad_norm": 0.5951201319694519,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.3469,
+      "step": 47
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.640261173248291,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.3762,
+      "step": 48
+    },
+    {
+      "epoch": 0.2722222222222222,
+      "grad_norm": 0.7929377555847168,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.5202,
+      "step": 49
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.8256304860115051,
+      "learning_rate": 0.0,
+      "loss": 0.5009,
+      "step": 50
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "eval_loss": 0.41205424070358276,
+      "eval_runtime": 16.6074,
+      "eval_samples_per_second": 18.245,
+      "eval_steps_per_second": 2.288,
+      "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": 1.398077353099264e+17,
+  "total_flos": 2.796154706198528e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null