Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eaaa8db05dbf519f7d6fbd76a77f073821159b9b6153e2f3cca57eb5901a9d9
+oid sha256:faa2989f4663e8e666822ee4f3734659326adba99ffe59054d26e326c7f233f9
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c282fe9a0123d12950fcf717dc82143aa4b42ed3b81b561682b0e22663da6fc
+oid sha256:ab17a764518f68dbe8aa204d0416328f689cdd34cf9114e049502e80b847b9a7
 size 60837186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1dafafab826c47d1f42713b8a2d5ef2135dc82204c8558d9ead76343070302b
+oid sha256:f4dad2115a2582d643a56aa7d50739e5d6edca2f0c06f3eebd9ae7f7367c4a99
 size 14244

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": 0.9804576635360718,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017448961786773687,
+  "best_metric": 0.8060246706008911,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.034897923573547374,
   "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": 13.276,
       "eval_steps_per_second": 6.638,
       "step": 25
+    },
+    {
+      "epoch": 0.018146920258244634,
+      "grad_norm": 9.390534400939941,
+      "learning_rate": 0.0001,
+      "loss": 0.9165,
+      "step": 26
+    },
+    {
+      "epoch": 0.018844878729715582,
+      "grad_norm": 9.242115020751953,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.7231,
+      "step": 27
+    },
+    {
+      "epoch": 0.01954283720118653,
+      "grad_norm": 9.97008991241455,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.89,
+      "step": 28
+    },
+    {
+      "epoch": 0.020240795672657477,
+      "grad_norm": 7.491469860076904,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.842,
+      "step": 29
+    },
+    {
+      "epoch": 0.020938754144128425,
+      "grad_norm": 11.089756965637207,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.1112,
+      "step": 30
+    },
+    {
+      "epoch": 0.021636712615599372,
+      "grad_norm": 11.30197811126709,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.5563,
+      "step": 31
+    },
+    {
+      "epoch": 0.02233467108707032,
+      "grad_norm": 5.173059463500977,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.6147,
+      "step": 32
+    },
+    {
+      "epoch": 0.023032629558541268,
+      "grad_norm": 7.637121200561523,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.7262,
+      "step": 33
+    },
+    {
+      "epoch": 0.023730588030012215,
+      "grad_norm": 7.962845802307129,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7012,
+      "step": 34
+    },
+    {
+      "epoch": 0.024428546501483163,
+      "grad_norm": 9.41506290435791,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.7252,
+      "step": 35
+    },
+    {
+      "epoch": 0.02512650497295411,
+      "grad_norm": 9.710718154907227,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.8126,
+      "step": 36
+    },
+    {
+      "epoch": 0.025824463444425058,
+      "grad_norm": 7.245460033416748,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.6849,
+      "step": 37
+    },
+    {
+      "epoch": 0.026522421915896006,
+      "grad_norm": 8.509491920471191,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.6192,
+      "step": 38
+    },
+    {
+      "epoch": 0.027220380387366953,
+      "grad_norm": 6.999649524688721,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.5379,
+      "step": 39
+    },
+    {
+      "epoch": 0.027918338858837898,
+      "grad_norm": 4.450455665588379,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.5619,
+      "step": 40
+    },
+    {
+      "epoch": 0.028616297330308845,
+      "grad_norm": 7.4137396812438965,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.7306,
+      "step": 41
+    },
+    {
+      "epoch": 0.029314255801779793,
+      "grad_norm": 4.460165023803711,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.3986,
+      "step": 42
+    },
+    {
+      "epoch": 0.03001221427325074,
+      "grad_norm": 5.552957057952881,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.8173,
+      "step": 43
+    },
+    {
+      "epoch": 0.030710172744721688,
+      "grad_norm": 4.119052886962891,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.7262,
+      "step": 44
+    },
+    {
+      "epoch": 0.03140813121619264,
+      "grad_norm": 6.945855617523193,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.5857,
+      "step": 45
+    },
+    {
+      "epoch": 0.03210608968766358,
+      "grad_norm": 7.324554443359375,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.7503,
+      "step": 46
+    },
+    {
+      "epoch": 0.032804048159134534,
+      "grad_norm": 11.844222068786621,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.6069,
+      "step": 47
+    },
+    {
+      "epoch": 0.03350200663060548,
+      "grad_norm": 3.3703107833862305,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.5407,
+      "step": 48
+    },
+    {
+      "epoch": 0.03419996510207643,
+      "grad_norm": 10.259138107299805,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.9289,
+      "step": 49
+    },
+    {
+      "epoch": 0.034897923573547374,
+      "grad_norm": 11.083820343017578,
+      "learning_rate": 0.0,
+      "loss": 0.9481,
+      "step": 50
+    },
+    {
+      "epoch": 0.034897923573547374,
+      "eval_loss": 0.8060246706008911,
+      "eval_runtime": 44.9024,
+      "eval_samples_per_second": 13.451,
+      "eval_steps_per_second": 6.726,
+      "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": 1553078629171200.0,
+  "total_flos": 3106157258342400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null