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:e8b518c14fa97b8cdbb9ebdb220f2d223d69ecd08ce1f3d1bc1fa8f45e446349
+oid sha256:d6a9699adaf7c6a749431ae2c5521ff449a1bd8089747a6b76442cf333a59906
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:942f1834b8e227e816a6e89fd5ea52460196122f4b7e6bff1caefeb5a0cbb3c0
+oid sha256:bfdcc779c4b1f60c8175017b2c2a8a19fe8ed39707a0ff32a8148219ba251950
 size 445914554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abe61778bde87cd8cc032c56410c7d8c3bad00b5c9dc35aeb4f9273c010176c
+oid sha256:7cd6cd6df02ad81aa6dcb41fb090c49481d7705cbca862c014256c90f9a9171f
 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": 1.0495991706848145,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0014053826154170473,
+  "best_metric": 1.0271567106246948,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0028107652308340947,
   "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": 0.963,
       "eval_steps_per_second": 0.481,
       "step": 25
+    },
+    {
+      "epoch": 0.0014615979200337291,
+      "grad_norm": 1.109177589416504,
+      "learning_rate": 0.0001,
+      "loss": 4.4231,
+      "step": 26
+    },
+    {
+      "epoch": 0.0015178132246504111,
+      "grad_norm": 1.3502737283706665,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 4.1029,
+      "step": 27
+    },
+    {
+      "epoch": 0.001574028529267093,
+      "grad_norm": 1.2638400793075562,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 4.4384,
+      "step": 28
+    },
+    {
+      "epoch": 0.001630243833883775,
+      "grad_norm": 1.253785490989685,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 3.7949,
+      "step": 29
+    },
+    {
+      "epoch": 0.0016864591385004567,
+      "grad_norm": 1.2122159004211426,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 4.5219,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017426744431171387,
+      "grad_norm": 1.1317585706710815,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 4.0376,
+      "step": 31
+    },
+    {
+      "epoch": 0.0017988897477338205,
+      "grad_norm": 3.269996404647827,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 4.1345,
+      "step": 32
+    },
+    {
+      "epoch": 0.0018551050523505025,
+      "grad_norm": 2.4214236736297607,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 3.9074,
+      "step": 33
+    },
+    {
+      "epoch": 0.0019113203569671843,
+      "grad_norm": 1.186686635017395,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.9877,
+      "step": 34
+    },
+    {
+      "epoch": 0.001967535661583866,
+      "grad_norm": 1.3781710863113403,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 4.4423,
+      "step": 35
+    },
+    {
+      "epoch": 0.002023750966200548,
+      "grad_norm": 1.2803940773010254,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 4.1471,
+      "step": 36
+    },
+    {
+      "epoch": 0.00207996627081723,
+      "grad_norm": 1.5898265838623047,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 4.409,
+      "step": 37
+    },
+    {
+      "epoch": 0.002136181575433912,
+      "grad_norm": 1.3593076467514038,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.7433,
+      "step": 38
+    },
+    {
+      "epoch": 0.0021923968800505937,
+      "grad_norm": 1.3938697576522827,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 4.0942,
+      "step": 39
+    },
+    {
+      "epoch": 0.0022486121846672755,
+      "grad_norm": 1.291236162185669,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 4.0084,
+      "step": 40
+    },
+    {
+      "epoch": 0.0023048274892839577,
+      "grad_norm": 1.3661845922470093,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 4.1608,
+      "step": 41
+    },
+    {
+      "epoch": 0.0023610427939006395,
+      "grad_norm": 1.5577927827835083,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 4.073,
+      "step": 42
+    },
+    {
+      "epoch": 0.0024172580985173213,
+      "grad_norm": 1.5352163314819336,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 4.3885,
+      "step": 43
+    },
+    {
+      "epoch": 0.002473473403134003,
+      "grad_norm": 1.6036438941955566,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 4.3737,
+      "step": 44
+    },
+    {
+      "epoch": 0.0025296887077506853,
+      "grad_norm": 1.6673026084899902,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 4.0295,
+      "step": 45
+    },
+    {
+      "epoch": 0.002585904012367367,
+      "grad_norm": 1.7688616514205933,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 4.6062,
+      "step": 46
+    },
+    {
+      "epoch": 0.002642119316984049,
+      "grad_norm": 1.910326600074768,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 5.2657,
+      "step": 47
+    },
+    {
+      "epoch": 0.0026983346216007307,
+      "grad_norm": 2.360198736190796,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 4.7428,
+      "step": 48
+    },
+    {
+      "epoch": 0.002754549926217413,
+      "grad_norm": 1.9681812524795532,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 4.1981,
+      "step": 49
+    },
+    {
+      "epoch": 0.0028107652308340947,
+      "grad_norm": 3.8947713375091553,
+      "learning_rate": 0.0,
+      "loss": 5.1876,
+      "step": 50
+    },
+    {
+      "epoch": 0.0028107652308340947,
+      "eval_loss": 1.0271567106246948,
+      "eval_runtime": 7776.1879,
+      "eval_samples_per_second": 0.963,
+      "eval_steps_per_second": 0.482,
+      "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": 6.80842493952e+16,
+  "total_flos": 1.361684987904e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null