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:f20a3c3d6fc879141386be713bf563799220515aa2104638a8c5fc7d13c95c75
+oid sha256:46d74360565f50f2cdc7f8b3a8dd241d958c390c5bd2724c757b2ef666e745e8
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31f6cbb39a1026ca677ae28f22ac83579812fb25a7359b7890042da8060f506
+oid sha256:2a2d39425986eabc5cb1e94fdd427717ea495bbb4a376367e752b7f44edeeb2c
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea8dc5080302285c5bbf05f4b2b6ad3afeb3edcc348bd7ec214a5e7b8903956
+oid sha256:0b4b36b222205ab059bec55ed86a12aa43ee689c98a67b66e4c4ce805185974b
 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": 0.03981335088610649,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.003852376916557516,
+  "best_metric": 0.03069155290722847,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.007704753833115032,
   "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": 13.793,
       "eval_steps_per_second": 6.899,
       "step": 25
+    },
+    {
+      "epoch": 0.0040064719932198165,
+      "grad_norm": 0.12516999244689941,
+      "learning_rate": 0.0001,
+      "loss": 0.0014,
+      "step": 26
+    },
+    {
+      "epoch": 0.004160567069882117,
+      "grad_norm": 1.0549215078353882,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0065,
+      "step": 27
+    },
+    {
+      "epoch": 0.004314662146544418,
+      "grad_norm": 0.15887008607387543,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0006,
+      "step": 28
+    },
+    {
+      "epoch": 0.004468757223206718,
+      "grad_norm": 0.11489447951316833,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0011,
+      "step": 29
+    },
+    {
+      "epoch": 0.00462285229986902,
+      "grad_norm": 0.046903226524591446,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0006,
+      "step": 30
+    },
+    {
+      "epoch": 0.00477694737653132,
+      "grad_norm": 2.046870708465576,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.051,
+      "step": 31
+    },
+    {
+      "epoch": 0.004931042453193621,
+      "grad_norm": 2.493454694747925,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0383,
+      "step": 32
+    },
+    {
+      "epoch": 0.005085137529855921,
+      "grad_norm": 4.297386169433594,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.1849,
+      "step": 33
+    },
+    {
+      "epoch": 0.005239232606518222,
+      "grad_norm": 0.09642432630062103,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0011,
+      "step": 34
+    },
+    {
+      "epoch": 0.005393327683180522,
+      "grad_norm": 1.7153476476669312,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0206,
+      "step": 35
+    },
+    {
+      "epoch": 0.005547422759842823,
+      "grad_norm": 0.22341029345989227,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0035,
+      "step": 36
+    },
+    {
+      "epoch": 0.0057015178365051235,
+      "grad_norm": 0.19758951663970947,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0024,
+      "step": 37
+    },
+    {
+      "epoch": 0.005855612913167424,
+      "grad_norm": 1.3141134977340698,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0184,
+      "step": 38
+    },
+    {
+      "epoch": 0.006009707989829725,
+      "grad_norm": 0.03539599850773811,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0006,
+      "step": 39
+    },
+    {
+      "epoch": 0.006163803066492025,
+      "grad_norm": 1.2810553312301636,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0069,
+      "step": 40
+    },
+    {
+      "epoch": 0.006317898143154326,
+      "grad_norm": 0.6757269501686096,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0112,
+      "step": 41
+    },
+    {
+      "epoch": 0.006471993219816627,
+      "grad_norm": 0.5809444785118103,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0048,
+      "step": 42
+    },
+    {
+      "epoch": 0.006626088296478928,
+      "grad_norm": 0.2564387321472168,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0039,
+      "step": 43
+    },
+    {
+      "epoch": 0.006780183373141228,
+      "grad_norm": 0.2768235206604004,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0026,
+      "step": 44
+    },
+    {
+      "epoch": 0.006934278449803529,
+      "grad_norm": 2.1270205974578857,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0365,
+      "step": 45
+    },
+    {
+      "epoch": 0.0070883735264658295,
+      "grad_norm": 2.755265235900879,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.1414,
+      "step": 46
+    },
+    {
+      "epoch": 0.00724246860312813,
+      "grad_norm": 0.03143172711133957,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0005,
+      "step": 47
+    },
+    {
+      "epoch": 0.007396563679790431,
+      "grad_norm": 2.56762433052063,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.1278,
+      "step": 48
+    },
+    {
+      "epoch": 0.007550658756452731,
+      "grad_norm": 2.4865427017211914,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.1046,
+      "step": 49
+    },
+    {
+      "epoch": 0.007704753833115032,
+      "grad_norm": 0.07366398721933365,
+      "learning_rate": 0.0,
+      "loss": 0.0014,
+      "step": 50
+    },
+    {
+      "epoch": 0.007704753833115032,
+      "eval_loss": 0.03069155290722847,
+      "eval_runtime": 198.1456,
+      "eval_samples_per_second": 13.793,
+      "eval_steps_per_second": 6.899,
+      "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": 1802385752064000.0,
+  "total_flos": 3604771504128000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null