Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d0abc7e70fc8e4bceb1dd9e7145d80eccb6afdc8464179e0847d382b46092e
+oid sha256:58ba7861c6df63142e2078ce228121e5ad4bb45cca8ac76bdefe5b8d1e85534a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed4945b9309eaae1cdb28763ad6d768839f931f4b8c560facdce4d170c872ad
+oid sha256:eb489a7db7e20413544488539907b559b11bcddadd82c70cee9d82c5feb31872
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:904ad5f613c15da991cdf19ae728e9872688971e6cbfce0f20a97d95fad2e564
+oid sha256:c0e46294980d979415c8ce20772ca3403e7626dbf4a0e3d023bad16ba253b711
 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": 0.757265567779541,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017114495978093443,
+  "best_metric": 0.7463985085487366,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03422899195618689,
   "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": 3.507,
       "eval_steps_per_second": 1.756,
       "step": 25
+    },
+    {
+      "epoch": 0.017799075817217184,
+      "grad_norm": 0.7362199425697327,
+      "learning_rate": 0.0001,
+      "loss": 0.7578,
+      "step": 26
+    },
+    {
+      "epoch": 0.01848365565634092,
+      "grad_norm": 0.7891442179679871,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.8214,
+      "step": 27
+    },
+    {
+      "epoch": 0.019168235495464658,
+      "grad_norm": 0.7279160022735596,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.6954,
+      "step": 28
+    },
+    {
+      "epoch": 0.019852815334588398,
+      "grad_norm": 0.7480013966560364,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.7565,
+      "step": 29
+    },
+    {
+      "epoch": 0.020537395173712135,
+      "grad_norm": 0.6995139122009277,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.7785,
+      "step": 30
+    },
+    {
+      "epoch": 0.021221975012835872,
+      "grad_norm": 0.7900039553642273,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.856,
+      "step": 31
+    },
+    {
+      "epoch": 0.02190655485195961,
+      "grad_norm": 0.775541365146637,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.8656,
+      "step": 32
+    },
+    {
+      "epoch": 0.02259113469108335,
+      "grad_norm": 0.7846947312355042,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.7725,
+      "step": 33
+    },
+    {
+      "epoch": 0.023275714530207086,
+      "grad_norm": 0.7840977311134338,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6967,
+      "step": 34
+    },
+    {
+      "epoch": 0.023960294369330823,
+      "grad_norm": 0.7890691757202148,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.799,
+      "step": 35
+    },
+    {
+      "epoch": 0.02464487420845456,
+      "grad_norm": 0.9354871511459351,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.7397,
+      "step": 36
+    },
+    {
+      "epoch": 0.0253294540475783,
+      "grad_norm": 0.8776700496673584,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.7285,
+      "step": 37
+    },
+    {
+      "epoch": 0.026014033886702037,
+      "grad_norm": 0.8412185311317444,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.6084,
+      "step": 38
+    },
+    {
+      "epoch": 0.026698613725825774,
+      "grad_norm": 0.9186910390853882,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.9773,
+      "step": 39
+    },
+    {
+      "epoch": 0.02738319356494951,
+      "grad_norm": 0.8276947736740112,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.8109,
+      "step": 40
+    },
+    {
+      "epoch": 0.02806777340407325,
+      "grad_norm": 0.8860321044921875,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.7461,
+      "step": 41
+    },
+    {
+      "epoch": 0.028752353243196988,
+      "grad_norm": 0.9271875619888306,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.8198,
+      "step": 42
+    },
+    {
+      "epoch": 0.029436933082320725,
+      "grad_norm": 0.9980719089508057,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.715,
+      "step": 43
+    },
+    {
+      "epoch": 0.030121512921444462,
+      "grad_norm": 0.8296429514884949,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.7061,
+      "step": 44
+    },
+    {
+      "epoch": 0.030806092760568202,
+      "grad_norm": 0.9510181546211243,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.7851,
+      "step": 45
+    },
+    {
+      "epoch": 0.03149067259969194,
+      "grad_norm": 1.0919767618179321,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.9219,
+      "step": 46
+    },
+    {
+      "epoch": 0.03217525243881568,
+      "grad_norm": 1.0661510229110718,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.6854,
+      "step": 47
+    },
+    {
+      "epoch": 0.03285983227793941,
+      "grad_norm": 1.2622677087783813,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.9412,
+      "step": 48
+    },
+    {
+      "epoch": 0.03354441211706315,
+      "grad_norm": 1.1761354207992554,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.616,
+      "step": 49
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "grad_norm": 1.9178863763809204,
+      "learning_rate": 0.0,
+      "loss": 0.7909,
+      "step": 50
+    },
+    {
+      "epoch": 0.03422899195618689,
+      "eval_loss": 0.7463985085487366,
+      "eval_runtime": 175.2305,
+      "eval_samples_per_second": 3.51,
+      "eval_steps_per_second": 1.758,
+      "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