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:d1e3a2d1c23e50291fa8fde17bed40523ed1d254d7430b367e9dd4eeb10a1085
+oid sha256:7cf5f4d31384a3c0ca5a299f6a055b7eb74a1bcd733156114ece0eed853b0f3b
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8be41e272d521f73c59e3fe74037acf5f24c3f1653bfad499122c3b7ff8d0a
+oid sha256:985e6ba709cde3df6e4e8f48ff72a37f06011e963a1545404e47149811976eb9
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd21d02659ecb4f1baba74d0c0b7bff1a11ed1d3703877c7093585c1988426f
+oid sha256:740a02d23889ae8f047363fc680623de9a1de2d247f747f842729a3c2a00b473
 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": 2.594191312789917,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12437810945273632,
+  "best_metric": 2.515887498855591,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.24875621890547264,
   "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": 13.799,
       "eval_steps_per_second": 6.981,
       "step": 25
+    },
+    {
+      "epoch": 0.12935323383084577,
+      "grad_norm": 3.9420931339263916,
+      "learning_rate": 0.0001,
+      "loss": 2.5456,
+      "step": 26
+    },
+    {
+      "epoch": 0.13432835820895522,
+      "grad_norm": 5.832747936248779,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 2.1194,
+      "step": 27
+    },
+    {
+      "epoch": 0.13930348258706468,
+      "grad_norm": 5.003444194793701,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.3539,
+      "step": 28
+    },
+    {
+      "epoch": 0.14427860696517414,
+      "grad_norm": 3.70873761177063,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.5001,
+      "step": 29
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 3.857776403427124,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.3172,
+      "step": 30
+    },
+    {
+      "epoch": 0.15422885572139303,
+      "grad_norm": 3.669508934020996,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 2.1357,
+      "step": 31
+    },
+    {
+      "epoch": 0.15920398009950248,
+      "grad_norm": 7.074223518371582,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 3.0023,
+      "step": 32
+    },
+    {
+      "epoch": 0.16417910447761194,
+      "grad_norm": 4.587769508361816,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.2561,
+      "step": 33
+    },
+    {
+      "epoch": 0.1691542288557214,
+      "grad_norm": 4.273606777191162,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.448,
+      "step": 34
+    },
+    {
+      "epoch": 0.17412935323383086,
+      "grad_norm": 4.296418190002441,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 2.3099,
+      "step": 35
+    },
+    {
+      "epoch": 0.1791044776119403,
+      "grad_norm": 3.6311933994293213,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.3837,
+      "step": 36
+    },
+    {
+      "epoch": 0.18407960199004975,
+      "grad_norm": 4.1932902336120605,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.6655,
+      "step": 37
+    },
+    {
+      "epoch": 0.1890547263681592,
+      "grad_norm": 4.752549171447754,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.6488,
+      "step": 38
+    },
+    {
+      "epoch": 0.19402985074626866,
+      "grad_norm": 4.613941669464111,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.5856,
+      "step": 39
+    },
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 4.24809455871582,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.2621,
+      "step": 40
+    },
+    {
+      "epoch": 0.20398009950248755,
+      "grad_norm": 4.745845794677734,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.2354,
+      "step": 41
+    },
+    {
+      "epoch": 0.208955223880597,
+      "grad_norm": 5.25393009185791,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.6063,
+      "step": 42
+    },
+    {
+      "epoch": 0.21393034825870647,
+      "grad_norm": 4.762695789337158,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.3609,
+      "step": 43
+    },
+    {
+      "epoch": 0.21890547263681592,
+      "grad_norm": 4.703743934631348,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.2418,
+      "step": 44
+    },
+    {
+      "epoch": 0.22388059701492538,
+      "grad_norm": 5.409986972808838,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.1651,
+      "step": 45
+    },
+    {
+      "epoch": 0.22885572139303484,
+      "grad_norm": 4.685298442840576,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.1631,
+      "step": 46
+    },
+    {
+      "epoch": 0.23383084577114427,
+      "grad_norm": 6.100794315338135,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.3216,
+      "step": 47
+    },
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 4.347185134887695,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.1609,
+      "step": 48
+    },
+    {
+      "epoch": 0.24378109452736318,
+      "grad_norm": 5.658843040466309,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.4468,
+      "step": 49
+    },
+    {
+      "epoch": 0.24875621890547264,
+      "grad_norm": 5.9395833015441895,
+      "learning_rate": 0.0,
+      "loss": 2.4286,
+      "step": 50
+    },
+    {
+      "epoch": 0.24875621890547264,
+      "eval_loss": 2.515887498855591,
+      "eval_runtime": 6.187,
+      "eval_samples_per_second": 13.739,
+      "eval_steps_per_second": 6.95,
+      "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