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:ada9d9b4cbf9a33beeef9640fd61a1841714e621d2b8fb30cb441b9b9b08951c
+oid sha256:2bec708afcacf52770c0622aeab24bf255d4da168a8c7e01fa94d7b0f9d59a2c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68459fa2d67385e59edec531804640ea8a6f92ba16938ece9a585481fc94bd37
+oid sha256:933f746ea19f9aa013a3031d490b06c51f2f9f2b7fa9e4ba7db24c98b1cd85a3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e350d80d5ded9f08f9e26666802eeccf41656dce8ce9016f7c1932c30d5387
+oid sha256:c6ed65badc7b7658e6174395316fb7b5b85d78a353fb9f52c928c254e823a705
 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": 0.5781829953193665,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11389521640091116,
+  "best_metric": 0.5658515095710754,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22779043280182232,
   "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": 2.846,
       "eval_steps_per_second": 1.438,
       "step": 25
+    },
+    {
+      "epoch": 0.11845102505694761,
+      "grad_norm": 0.5211344361305237,
+      "learning_rate": 0.0001,
+      "loss": 0.5899,
+      "step": 26
+    },
+    {
+      "epoch": 0.12300683371298406,
+      "grad_norm": 0.5211654305458069,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.5972,
+      "step": 27
+    },
+    {
+      "epoch": 0.1275626423690205,
+      "grad_norm": 0.5849275588989258,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.5839,
+      "step": 28
+    },
+    {
+      "epoch": 0.13211845102505695,
+      "grad_norm": 0.4501253068447113,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.5529,
+      "step": 29
+    },
+    {
+      "epoch": 0.1366742596810934,
+      "grad_norm": 0.49339428544044495,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.5871,
+      "step": 30
+    },
+    {
+      "epoch": 0.14123006833712984,
+      "grad_norm": 0.5657844543457031,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.5959,
+      "step": 31
+    },
+    {
+      "epoch": 0.14578587699316628,
+      "grad_norm": 0.4766876995563507,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.5395,
+      "step": 32
+    },
+    {
+      "epoch": 0.15034168564920272,
+      "grad_norm": 0.564814567565918,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.4958,
+      "step": 33
+    },
+    {
+      "epoch": 0.1548974943052392,
+      "grad_norm": 0.5830087661743164,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4789,
+      "step": 34
+    },
+    {
+      "epoch": 0.15945330296127563,
+      "grad_norm": 0.5815562009811401,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.6065,
+      "step": 35
+    },
+    {
+      "epoch": 0.16400911161731208,
+      "grad_norm": 0.6064615249633789,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.6396,
+      "step": 36
+    },
+    {
+      "epoch": 0.16856492027334852,
+      "grad_norm": 0.5316784977912903,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.5774,
+      "step": 37
+    },
+    {
+      "epoch": 0.17312072892938496,
+      "grad_norm": 0.48915421962738037,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.4591,
+      "step": 38
+    },
+    {
+      "epoch": 0.1776765375854214,
+      "grad_norm": 0.5418641567230225,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.5223,
+      "step": 39
+    },
+    {
+      "epoch": 0.18223234624145787,
+      "grad_norm": 0.5213112235069275,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.5117,
+      "step": 40
+    },
+    {
+      "epoch": 0.1867881548974943,
+      "grad_norm": 0.5756207704544067,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.6081,
+      "step": 41
+    },
+    {
+      "epoch": 0.19134396355353075,
+      "grad_norm": 0.6244314312934875,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.5689,
+      "step": 42
+    },
+    {
+      "epoch": 0.1958997722095672,
+      "grad_norm": 0.5913732051849365,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.5987,
+      "step": 43
+    },
+    {
+      "epoch": 0.20045558086560364,
+      "grad_norm": 0.5238770246505737,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.515,
+      "step": 44
+    },
+    {
+      "epoch": 0.20501138952164008,
+      "grad_norm": 0.6109748482704163,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.5994,
+      "step": 45
+    },
+    {
+      "epoch": 0.20956719817767655,
+      "grad_norm": 0.6811307072639465,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.6176,
+      "step": 46
+    },
+    {
+      "epoch": 0.214123006833713,
+      "grad_norm": 0.7551108002662659,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.7899,
+      "step": 47
+    },
+    {
+      "epoch": 0.21867881548974943,
+      "grad_norm": 0.7084043622016907,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.72,
+      "step": 48
+    },
+    {
+      "epoch": 0.22323462414578588,
+      "grad_norm": 0.704668402671814,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.5994,
+      "step": 49
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 0.8863475918769836,
+      "learning_rate": 0.0,
+      "loss": 0.6488,
+      "step": 50
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "eval_loss": 0.5658515095710754,
+      "eval_runtime": 32.7361,
+      "eval_samples_per_second": 2.841,
+      "eval_steps_per_second": 1.436,
+      "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": 3.70943641780224e+16,
+  "total_flos": 7.41887283560448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null